ai.uselamina/lamina

Official27 tools

by uselamina

On-brand product photos, model try-ons, video reels & banners from a brief + brand kit.

MCP Server: ai.uselamina/lamina

The ai.uselamina/lamina MCP server provides tools for generating on-brand visual assets, including product photos, model try-ons, video reels, and banners based on a brief + brand kit. It is described as supporting these output types as its core functionality.

🛠️ Key Features

On-brand product photos
Model try-ons
Video reels
Banners
Asset creation driven by a brief + brand kit
27 tools

🚀 Use Cases

Produce product photo variations aligned with brand guidelines
Generate model try-on visuals from a provided brief and brand kit
Create video reels and banners for promotional materials

⚡ Developer Benefits

Predictable inputs: brief and brand kit
Toolset coverage across multiple media formats (photos, try-ons, video, banners)

Captured live from the server via tools/list.

lamina_discover

Discover Lamina apps (creative workflows) that can produce what the user wants. ALWAYS start here when the user asks to create new content — discover the right app first, then describe it, then run it. How to use it: 1. Provide an array of `keywords` describing the desired creative outcome. Be concrete: combine medium (image / video / audio), form (reel, banner, hero shot, headshot, voiceover), and context (ecommerce, social, lifestyle). Examples: ["product video", "reel", "9:16"], ["hero banner", "lifestyle photo"], ["voiceover", "narration"]. 2. Read the returned apps. Each entry shows the app's name, description, outputs, and estimated credit cost when known. Choose by PURPOSE match — does the app's actual delivery match the user's intent? Keyword overlap alone is not enough. 3. If no listed app fits, call this tool again with different / broader / more specific keywords. The catalog is large; rephrasing often surfaces matches you missed. 4. If after a few sensible searches you still cannot find a suitable app, tell the user honestly that the catalog has no app for this exact need — suggest the closest related app or propose they refine their goal. 5. Once a candidate looks right, call `lamina_describe` with its `appId` for the full parameter contract. The result is ordered by relevance. Apps may be owned by your workspace or shared publicly. `estimatedCredits` is omitted when it cannot be computed quickly — treat absence as "unknown", not zero.

Parameters3

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
keywords	array	required	Keywords describing the creative outcome. Combine medium + form + context for best results, e.g. ["product video", "reel", "9:16"] or ["hero banner", "lifestyle photo", "ecommerce"]. The more specific, the better the match.
limit	integer	optional	Maximum number of apps to return. Default 10.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "keywords": {
      "minItems": 1,
      "maxItems": 10,
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      },
      "description": "Keywords describing the creative outcome. Combine medium + form + context for best results, e.g. [\"product video\", \"reel\", \"9:16\"] or [\"hero banner\", \"lifestyle photo\", \"ecommerce\"]. The more specific, the better the match."
    },
    "limit": {
      "description": "Maximum number of apps to return. Default 10.",
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    }
  },
  "required": [
    "keywords"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_describe

Get the full input/output specification for a single Lamina app. Use it in the MANUAL flow (after `lamina_discover` and before `lamina_run`) when the calling LLM wants to inspect or verify an app's schema directly. The AGENTIC flow via `lamina_create` does discover + describe internally — no need to call describe before create. Returns: - `parameters[]` — every input the app accepts. Each entry has a stable `key` (used in `lamina_run.inputs`), a `type` (`text` / `options` / `url`), an optional `default`, and `accept`/`options`/`multiple` where relevant. - `outputs[]` — what the app produces. Each entry is `{ index, label, type: 'image'|'video'|'audio'|'text' }`. Labels are canonical identifiers — pass them verbatim to `lamina_run.outputs` when subsetting. - `estimatedCredits` — typical cost of one run (omitted when unknown). The user has NO form UI — they only see what you tell them in chat. Every parameter in `parameters[]` is something the workflow author wanted set; defaults shown are the AUTHOR's choices, not the user's authorization. Treat each parameter accordingly: - For USER-OWNED assets (their product, headshot, logo, brand asset, garment): never use the default. ASK the human in chat first — defaults here are demo placeholders that misrepresent the user's subject. - For PRESET / STYLE / REFERENCE groups (mood-board refs, style refs, palette refs, etc.) — often appearing as a numbered series of similar slots: ASK the human in chat ONCE per group — 'use the app's curated defaults or supply your own?' Don't silently default; the user can't see these slots exist. - For text/copy you can confidently draft from the brief (headlines, descriptions): draft. Otherwise ASK. - For dialog-derived settings (aspect ratio, variant count, output format): use the user's explicit input or hint; if absent, ASK. When in doubt about ANY parameter, ASK the human in chat before calling `lamina_run`. One extra question is cheaper than a wrong-output run. Constructing `inputs` for `lamina_run`: - Use the parameter `key` as the input key. Example: `inputs: { "your_photo_image_url": "https://..." }`. - For `type: "options"`, send the option label as a string (case-insensitive match). - For `type: "url"` with `multiple: true`, send an array of URLs. Otherwise send a single URL string. Never invent URLs. - Omit a parameter from `inputs` only when the user has explicitly authorized falling back to the workflow default.

Parameters2

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
appId	string	required	App ID returned by `lamina_discover`.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "appId": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "App ID returned by `lamina_discover`."
    }
  },
  "required": [
    "appId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_run

Dispatch a run for an app the user has authorized. Pure trigger — no LLM, no brief analysis, no app picking. Takes an `appId` you already know (from `lamina_create.selectedApp.appId` after the agentic flow, or from `lamina_describe` in the manual flow) plus `inputs` keyed by parameter `key`, optionally `outputs` (label subset). How to use it: - Pass `appId` and `inputs`. `inputs` is a map keyed by parameter `key` from describe (option label for `options`, URL string for `url`, array of URLs for `url + multiple`). - Only include parameters the user has explicitly authorized — by giving the value in the brief, answering an ask in chat, or saying 'use defaults' on a surfaced preset group. Silent defaults on user-owned slots produce wrong-subject output. - `outputs` (optional): when the user asked for only a subset of the app's outputs (e.g. 'just the front view and the lifestyle shot'), pass `outputs: ['Front View', 'Lifestyle View']` with labels verbatim from `lamina_describe.outputs[].label` (case-insensitive). Omit or pass an empty array to produce every output the app declares (default). - `applyBrand` (optional): set true to make the output on-brand — Lamina folds the workspace's brand negatives + visual style onto the app's visual nodes before running. Your `inputs` still win over brand. Use it instead of hand-writing brand into every input. - Returns immediately with `{runId, workflowId, status}`. Most apps take 1–5 minutes (median ~2 min, p90 ~5 min). Poll with `lamina_status`. - On `Invalid inputs` error, the response includes `details: [{param, code, message}]`. Common causes: option label not in declared list, malformed URL, wrong type. On `outputs_resolution_failed`, the label you passed doesn't match any output on the app — re-check `lamina_describe.outputs[].label`. - For variants/series (e.g. "5 selfies with different celebrities"), call this tool once per variant in parallel. Each call returns its own `runId`.

Parameters6

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
appId	string	required	App ID returned by `lamina_discover` and confirmed via `lamina_describe`.
inputs	object	required	Map keyed by parameter `key` (from `lamina_describe`). Values shaped per each parameter's type: option label for `options`, URL string for `url`, array of URLs for `url + multiple`. Only include parameters the user has explicitly authorized.
outputs	array	optional	Optional subset of the app's outputs to produce. Each entry is a `label` from `lamina_describe.outputs[].label` (case-insensitive). Omit or pass an empty array to produce every output the app declares.
applyBrand	boolean	optional	Fold the workspace's brand (negatives + visual style) onto the app's visual generation nodes so output is on-brand — without you weaving brand into `inputs`. Anything you pass in `inputs` still wins.
brandProfileId	string	optional	Target a specific brand profile when applyBrand is set. Defaults to the active brand.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "appId": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "App ID returned by `lamina_discover` and confirmed via `lamina_describe`."
    },
    "inputs": {
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {},
      "description": "Map keyed by parameter `key` (from `lamina_describe`). Values shaped per each parameter's type: option label for `options`, URL string for `url`, array of URLs for `url + multiple`. Only include parameters the user has explicitly authorized."
    },
    "outputs": {
      "description": "Optional subset of the app's outputs to produce. Each entry is a `label` from `lamina_describe.outputs[].label` (case-insensitive). Omit or pass an empty array to produce every output the app declares.",
      "type": "array",
      "items": {
        "type": "string",
        "minLength": 1
      }
    },
    "applyBrand": {
      "description": "Fold the workspace's brand (negatives + visual style) onto the app's visual generation nodes so output is on-brand — without you weaving brand into `inputs`. Anything you pass in `inputs` still wins.",
      "type": "boolean"
    },
    "brandProfileId": {
      "description": "Target a specific brand profile when applyBrand is set. Defaults to the active brand.",
      "type": "string"
    }
  },
  "required": [
    "appId",
    "inputs"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_status

Check the status of any Lamina run — polymorphic across atomic image-gen (`lamina_generate_image`), atomic video-gen (`lamina_generate_video`), app workflow runs (`lamina_run`), and agentic recipe runs. - Default: returns the current snapshot (`queued` / `running` / `completed` / `failed` / `cancelled`) and the result. The agent decides when to call again. - With `wait: true`: blocks server-side, polling every 2 seconds, until the run reaches a terminal state OR `timeoutSeconds` elapses (default 240, max 600). Atomic image runs typically finish in 5–30s; atomic video runs take 30s–5 min; app workflows 1–5 min (median ~2 min, p90 ~5 min). Pick `timeoutSeconds` accordingly. If the timeout fires, the response includes `"timeout": true` plus the current status; call again to keep waiting. Response shape depends on the run kind: - **Atomic image-gen runs**: when `completed`, the response has `output: { type: "image", url: "..." }` (singular). Pass the `url` to the user. - **Atomic video-gen runs**: when `completed`, the response has `output: { type: "video", url: "..." }` (singular). Pass the `url` to the user. - **App + freestyle runs**: when `completed`, every entry in `outputs[]` has a `url`. The `label` matches what you saw in `lamina_describe`. Pass URLs back to the user, or feed them into a follow-up `lamina_run` as reference assets. - When `failed`, `errorMessage` carries the top-level reason. Per-output failures (app runs) are in `outputs[i].error`. - While the run is `running`, surface progress to the user instead of making them wait silently.

Parameters4

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
runId	string	required	Run ID returned by `lamina_run` / `lamina_generate_image` / `lamina_generate_video` — pass it back exactly as given.
wait	boolean	optional	When true, the server polls internally and returns only when the run reaches a terminal state (or `timeoutSeconds` elapses). When false, returns the current snapshot immediately.
timeoutSeconds	integer	optional	Maximum server-side wait time when `wait: true`. Default 240, max 600. Real run durations: median ~2 min, p90 ~5 min — set higher for confidence the call returns the final result, lower if you want to surface intermediate progress to the user.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "runId": {
      "type": "string",
      "minLength": 1,
      "description": "Run ID returned by `lamina_run` / `lamina_generate_image` / `lamina_generate_video` — pass it back exactly as given."
    },
    "wait": {
      "default": false,
      "description": "When true, the server polls internally and returns only when the run reaches a terminal state (or `timeoutSeconds` elapses). When false, returns the current snapshot immediately.",
      "type": "boolean"
    },
    "timeoutSeconds": {
      "default": 240,
      "description": "Maximum server-side wait time when `wait: true`. Default 240, max 600. Real run durations: median ~2 min, p90 ~5 min — set higher for confidence the call returns the final result, lower if you want to surface intermediate progress to the user.",
      "type": "integer",
      "minimum": 1,
      "maximum": 600
    }
  },
  "required": [
    "runId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_models_list

List Lamina's curated atomic generation models. Each entry has `id`, `displayName`, `modality`, and — to help you pick deliberately rather than guess — `bestFor` (what the model is good at / when to reach for it), `cost` (`low`|`medium`|`high` relative credit tier), `speed` (`fast`|`standard`|`slow`), and `provider` (the infra that serves it: `fal`|`wavespeed`|`vertex`). Pass `modality: 'image'` (default) or `modality: 'video'` to scope the response. Use `bestFor` to match the task, and `cost`/`speed` to break ties — prefer a `low`/`fast` model unless the task needs the quality of a `high` one. After picking an `id`, call `lamina_models_describe({modelId})` to get the input contract before calling `lamina_generate_image` / `lamina_generate_video`.

Parameters2

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
modality	string	optional	"image" (default) or "video".

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "modality": {
      "default": "image",
      "description": "\"image\" (default) or \"video\".",
      "type": "string",
      "enum": [
        "image",
        "video"
      ]
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_models_describe

Get the input contract for one atomic-generate model (image OR video). Returns `id`, `displayName`, `modality`, and a flat `paramSchema` (every accepted field, including `prompt`, with `type`, allowed `values`, `default`, `min`/`max`/`step`, and short field-level `description` text). Hybrid models present a single merged schema where mode-specific fields are marked optional; the description on each field tells you when it applies. Models that don't accept a prompt (e.g. `bria-bg-remove`) simply omit the `prompt` field from `paramSchema`. Polymorphic — tries image registry then video registry, so any id from `lamina_models_list({modality:'image'|'video'})` is accepted. Call this BEFORE `lamina_generate_image` / `lamina_generate_video` for a model you haven't used. The response is the contract — what you pass in `params` must match these field rules, and the cross-field constraints noted in each field's `description` (e.g. gpt-image-2's custom dimensions are capped at 8.3M pixels and 3:1 aspect).

Parameters2

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
modelId	string	required	Model id from `lamina_models_list`, e.g. "ideogram-v3" or "kling-v25-text-to-video".

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "modelId": {
      "type": "string",
      "minLength": 1,
      "description": "Model id from `lamina_models_list`, e.g. \"ideogram-v3\" or \"kling-v25-text-to-video\"."
    }
  },
  "required": [
    "modelId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_generate_image

Dispatch a single atomic image generation. Sibling of `lamina_create` (the agentic router) — use this when you already know which model fits, or when no app fits the brief. WORKFLOW: (1) `lamina_models_list({ modality: "image" })` → pick a model. (2) `lamina_models_describe({ modelId })` → read its flat `paramSchema`. (3) `lamina_generate_image({ model, prompt, params })` → dispatch, get runId. (4) `lamina_status({ runId, wait: true })` → poll until completed; the response has `output.url`. ONE TOOL, BOTH OPERATIONS: • Text-to-image — call with just `prompt` (and any text-mode params). The model id you picked is the only thing that selects the operation. • Image-to-image (edit / remix / background-swap / etc.) — call the same tool, but include a source image in `params`. Hybrid models (nano-banana-pro, gpt-image-2, gemini-2.5-flash-image, seedream-4.5, flux-2-flex, nano-banana-2, gpt-image-1, gpt-image-1.5) flip to image-to-image automatically when `params.imageUrls` is a non-empty array (or `params.imageUrl` is set for single-source models like flux-pro-kontext). Edit-only models (bria-bg-remove, ideogram-character, ideogram-v3-remix/reframe/replace-background, flux-pro-kontext, ideogram-character-remix) only have image-to-image — `params.imageUrls`/`imageUrl` is required. INPUTS: • `model` (required): a model id from `lamina_models_list`. Don't invent it. • `prompt` (required for most models; check `paramSchema.prompt.required` from `lamina_models_describe`; absent from `paramSchema` for prompt-less models like `bria-bg-remove` and `ideogram-v3-reframe`): natural-language brief; ≤2000 chars. • `params` (model-specific): every key MUST be declared in the chosen model's `paramSchema` (call `lamina_models_describe` first). Unknown keys are rejected with a structured `invalid_params` error; each error has `field` + `allowed`/`range`/`got` so you can correct on retry. Omitted optional keys fall back to schema defaults. • `webhookUrl` (optional): HTTPS URL. On terminal status Lamina POSTs `{runId, status, model, prompt, resolvedParams, output, errorMessage, completedAt}` HMAC-signed. RESPONSE: `{runId, status: "queued"|"completed", model, mode, prompt, resolvedParams}`. `mode` is the resolved value ("text-to-image" | "image-to-image"). The `runId` is the fal_request_id — pass it to `lamina_status`. SYNC vs ASYNC: identical contract. Vertex-backed models (`imagen-4.0-*`, `gemini-2.5-flash-image`) complete in seconds and return `status: "completed"` on the first poll. fal-backed models queue and take 5–60s. `lamina_status({ wait: true })` handles both transparently. ERROR HANDLING: validation failures return `code` + `details.errors[]` with `field` + `error` + `allowed`/`range`/`got`. Common codes: `model_not_supported`, `mode_not_supported`, `invalid_params`, `dispatch_failed`.

Parameters5

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
model	string	required	Model id from `lamina_models_list({modality:"image"})`.
prompt	string	optional	Natural-language prompt (≤2000). Required for most models; omit only for prompt-less edits.
params	object	optional	Model-specific fields per the chosen (model, mode)'s `paramSchema`. Include `imageUrls` (array) or `imageUrl` (string) when you want image-to-image; omit them for text-to-image. Call `lamina_models_describe({modelId})` to see what's accepted.
webhookUrl	string	optional	Optional HTTPS URL to POST the completion event to.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "model": {
      "type": "string",
      "minLength": 1,
      "description": "Model id from `lamina_models_list({modality:\"image\"})`."
    },
    "prompt": {
      "description": "Natural-language prompt (≤2000). Required for most models; omit only for prompt-less edits.",
      "type": "string",
      "maxLength": 2000
    },
    "params": {
      "description": "Model-specific fields per the chosen (model, mode)'s `paramSchema`. Include `imageUrls` (array) or `imageUrl` (string) when you want image-to-image; omit them for text-to-image. Call `lamina_models_describe({modelId})` to see what's accepted.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "webhookUrl": {
      "description": "Optional HTTPS URL to POST the completion event to.",
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "model"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_generate_video

Dispatch a single atomic video generation. Sibling of `lamina_generate_image` — same shape, but outputs a video URL. WORKFLOW: (1) `lamina_models_list({ modality: "video" })` → pick a model. (2) `lamina_models_describe({ modelId })` → read its flat `paramSchema` to learn required inputs. (3) `lamina_generate_video({ model, prompt, params })` → dispatch, get runId. (4) `lamina_status({ runId, wait: true })` → poll until completed; the response has `output.url`. ONE TOOL, EVERY VIDEO OPERATION. Model id selects the operation; `params` matches the model's paramSchema: • Text-to-video — Kling t2v variants, Wan-2.6-text-to-video, Wan-turbo, Minimax, Seedance t2v, Veo3-text-to-video. Just `prompt` (+ duration / aspectRatio / etc. per the model). • Image-to-video — Kling i2v variants, Wan-2.6/turbo image-to-video, Minimax i2v, Seedance i2v (uses `startImageUrl`), `happy-horse-image-to-video`, `veo3-image-to-video` (sync). `params` includes `imageUrl` (or `startImageUrl` for Seedance, `firstFrameUrl` for Veo3 first-frame). • Keyframe — `veo3-keyframe-to-video` (sync). `params` requires `firstFrameUrl` AND `lastFrameUrl` — model interpolates between them. • Motion-control — `kling-v26-motion-control`, `kling-v26-motion-control-pro`. `params` requires `imageUrl` (character) AND `videoUrl` (motion reference). • Video-to-video (edit) — `wan-video-to-video`, Kling v2v variants. `params` requires `videoUrl` (source). • Reference-to-video — Kling/Seedance/Wan reference variants. `params` uses `referenceImageUrls`. INPUTS: • `model` (required): a model id from `lamina_models_list({modality:"video"})`. • `prompt`: most models require it; some (motion-control variants) are optional. Check `paramSchema.prompt.required` from `lamina_models_describe`. Some models omit `prompt` from `paramSchema` entirely (prompt-less). • `params`: model-specific fields per the model's `paramSchema`. Required URL fields vary by operation — see list above. • `webhookUrl` (optional): HTTPS URL for HMAC-signed completion POST. • `includeCitationKit` (optional, PREVIEW): set `true` to request a citation-ready kit alongside the video — cleaned transcript, question-formatted chapters, a 30–60 word summary, and drop-in `VideoObject` JSON-LD — so wherever you host the video it is answer-engine-citable. Preview signal only: it records interest and returns a `coming_soon` note; the kit is not yet produced. RESPONSE: `{runId, status: "queued"|"completed", model, mode, prompt, resolvedParams}`. `mode` is the resolved operation. Pass `runId` to `lamina_status`. If `includeCitationKit` was set, the response also carries `citationKit: {status: "coming_soon"}`. SYNC vs ASYNC: identical contract. Veo3 variants (`veo3-text-to-video`, `veo3-image-to-video`, `veo3-first-frame-to-video`, `veo3-keyframe-to-video`) are Vertex-backed and complete in seconds. fal-backed models queue and take 30s–5min. `lamina_status({ wait: true, timeoutSeconds: 240 })` handles either transparently. ERROR HANDLING: same shape as `lamina_generate_image` — `code` + `details.errors[]` with `field` + `allowed`/`range`/`got`.

Parameters6

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
model	string	required	Model id from `lamina_models_list({modality:"video"})`.
prompt	string	optional	Natural-language prompt (≤2000). Required for most models; check the model's describe response for `prompt.required`.
params	object	optional	Model-specific fields per the chosen model's `paramSchema`. Required URL fields depend on the operation — e.g. `imageUrl` (image-to-video), `videoUrl` (video-to-video), both for motion-control, `firstFrameUrl`+`lastFrameUrl` for keyframe.
webhookUrl	string	optional	Optional HTTPS URL to POST the completion event to.
includeCitationKit	boolean	optional	PREVIEW: request a citation-ready kit (transcript, question-formatted chapters, 30–60w summary, VideoObject JSON-LD) so the video is answer-engine-citable wherever you host it. Preview flag — records interest and returns a `coming_soon` note; not yet fulfilled.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "model": {
      "type": "string",
      "minLength": 1,
      "description": "Model id from `lamina_models_list({modality:\"video\"})`."
    },
    "prompt": {
      "description": "Natural-language prompt (≤2000). Required for most models; check the model's describe response for `prompt.required`.",
      "type": "string",
      "maxLength": 2000
    },
    "params": {
      "description": "Model-specific fields per the chosen model's `paramSchema`. Required URL fields depend on the operation — e.g. `imageUrl` (image-to-video), `videoUrl` (video-to-video), both for motion-control, `firstFrameUrl`+`lastFrameUrl` for keyframe.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "webhookUrl": {
      "description": "Optional HTTPS URL to POST the completion event to.",
      "type": "string",
      "format": "uri"
    },
    "includeCitationKit": {
      "description": "PREVIEW: request a citation-ready kit (transcript, question-formatted chapters, 30–60w summary, VideoObject JSON-LD) so the video is answer-engine-citable wherever you host it. Preview flag — records interest and returns a `coming_soon` note; not yet fulfilled.",
      "type": "boolean"
    }
  },
  "required": [
    "model"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_plv_background

Generate a category-matched background plate for a Meta PLV (Product-Led-Video) ad. WHAT IT DOES: product attributes → LLM background brief (category-level, not SKU) → background-only image dispatch. The plate deliberately contains NO product, NO people and NO text — it leaves clean negative space so Meta can composite the product cutout on top. Colours are chosen to harmonise with the product colour (pink apparel → soft pink set; summer dress → sunlit coastal scene). WORKFLOW: (1) `lamina_plv_background({ product, aspectRatio })` → dispatch, get runId. (2) `lamina_status({ runId, wait: true })` → poll; `output.url` is the plate. INPUTS: • `product` (required): `{ category (required), color?, season?, occasion?, description? }`. `category` drives the scene; `color` drives the palette harmony; `season`/`occasion` steer the setting. • `theme` (optional): `{ label?, cue? }` — the ~monthly thematic event this creative runs in (e.g. label "Diwali", cue "festive gifting"), folded into the brief. • `aspectRatio` (optional, default `9:16`): PLV plate ratio. `4:5` maps to the nearest supported portrait preset. • `model` (optional): image model id; defaults to a photoreal 4K backdrop model. • `webhookUrl` (optional): HTTPS URL POSTed on terminal status. RESPONSE: `{ runId, status, model, aspectRatio, brief, prompt, negativePrompt }`. `brief` is the structured art-direction the plate was generated from; `prompt` is the exact background-only prompt dispatched.

Parameters8

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
product	object	required	Product attributes. Category-level only — never a specific SKU.
theme	object	optional	Optional thematic-event hook (~4 events/month).
aspectRatio	string	optional	PLV plate aspect ratio. Default 9:16.
polish	string	optional	Production polish. `native` = intentionally rough/UGC (often wins on Meta); `premium` = high-end editorial. Default balanced.
brandProfileId	string	optional	Brand profile id to steer palette/tone toward a sub-brand (e.g. Forward / Lux / M Now). Resolved via your workspace brand profiles.
model	string	optional	Optional image model id override from `lamina_models_list`.
webhookUrl	string	optional	Optional HTTPS URL to POST the completion event to.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "product": {
      "type": "object",
      "properties": {
        "category": {
          "type": "string",
          "minLength": 1,
          "description": "Product category, e.g. \"summer dress\", \"running shoes\". Drives the scene."
        },
        "color": {
          "description": "Product colour — the plate palette is chosen to harmonise with it.",
          "type": "string"
        },
        "season": {
          "description": "Season, e.g. \"summer\", \"festive\".",
          "type": "string"
        },
        "occasion": {
          "description": "Occasion, e.g. \"wedding\", \"gym\", \"vacation\".",
          "type": "string"
        },
        "description": {
          "description": "Optional extra notes about the product.",
          "type": "string"
        }
      },
      "required": [
        "category"
      ],
      "description": "Product attributes. Category-level only — never a specific SKU."
    },
    "theme": {
      "description": "Optional thematic-event hook (~4 events/month).",
      "type": "object",
      "properties": {
        "label": {
          "description": "Thematic-event name, e.g. \"Diwali\".",
          "type": "string"
        },
        "cue": {
          "description": "Creative cue for the event, e.g. \"festive gifting\".",
          "type": "string"
        }
      }
    },
    "aspectRatio": {
      "description": "PLV plate aspect ratio. Default 9:16.",
      "type": "string",
      "enum": [
        "9:16",
        "4:5",
        "1:1",
        "16:9",
        "3:4",
        "2:3"
      ]
    },
    "polish": {
      "description": "Production polish. `native` = intentionally rough/UGC (often wins on Meta); `premium` = high-end editorial. Default balanced.",
      "type": "string",
      "enum": [
        "native",
        "balanced",
        "premium"
      ]
    },
    "brandProfileId": {
      "description": "Brand profile id to steer palette/tone toward a sub-brand (e.g. Forward / Lux / M Now). Resolved via your workspace brand profiles.",
      "type": "string"
    },
    "model": {
      "description": "Optional image model id override from `lamina_models_list`.",
      "type": "string",
      "minLength": 1
    },
    "webhookUrl": {
      "description": "Optional HTTPS URL to POST the completion event to.",
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "product"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_generate_hook

Generate a short (~4s) HOOK opener clip that plays BEFORE the product appears in a Meta ad. WHAT IT DOES: product category (+ optional vertical/theme) → LLM hook brief → text-to-video dispatch of a category-relevant human action (person knocking, kicking a football, applying makeup). The clip deliberately shows NO product, logo, price or text — it exists to stop the scroll; the product reveal comes after. WORKFLOW: (1) `lamina_generate_hook({ product, aspectRatio })` → dispatch, get runId. (2) `lamina_status({ runId, wait: true })` → poll; `output.url` is the clip. INPUTS: • `product` (required): `{ category (required), vertical? }`. `category` drives the action; `vertical` (e.g. "Forward", "Lux", "M Now") tunes the subject + tone. • `theme` (optional): `{ label?, cue? }` — thematic event to reflect. • `aspectRatio` (optional, default `9:16`). • `durationSeconds` (optional, default `4`; clamped to 4–12, the model floor/ceiling). • `model` (optional): video model id override. • `webhookUrl` (optional): HTTPS URL POSTed on terminal status. RESPONSE: `{ runId, status, model, aspectRatio, durationSeconds, brief, prompt, negativePrompt }`.

Parameters9

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
product	object	required	Product context. Category-level.
theme	object	optional	Optional thematic-event hook.
aspectRatio	string	optional	Clip aspect ratio. Default 9:16.
durationSeconds	integer	optional	Target clip length; clamped to the model floor of 4s and ceiling of 12s. Default 4.
polish	string	optional	Production polish. `native` = handheld/UGC energy (often wins on Meta); `premium` = cinematic. Default balanced.
brandProfileId	string	optional	Brand profile id to steer tone toward a sub-brand (e.g. Forward / Lux / M Now). Resolved via your workspace brand profiles.
model	string	optional	Optional video model id override from `lamina_models_list({modality:"video"})`.
webhookUrl	string	optional	Optional HTTPS URL to POST the completion event to.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "product": {
      "type": "object",
      "properties": {
        "category": {
          "type": "string",
          "minLength": 1,
          "description": "Product category, e.g. \"football boots\", \"lipstick\". Drives the hook action."
        },
        "vertical": {
          "description": "Vertical / sub-brand, e.g. \"Forward\", \"Lux\", \"M Now\" — tunes subject + tone.",
          "type": "string"
        }
      },
      "required": [
        "category"
      ],
      "description": "Product context. Category-level."
    },
    "theme": {
      "description": "Optional thematic-event hook.",
      "type": "object",
      "properties": {
        "label": {
          "description": "Thematic-event name.",
          "type": "string"
        },
        "cue": {
          "description": "Creative cue for the event.",
          "type": "string"
        }
      }
    },
    "aspectRatio": {
      "description": "Clip aspect ratio. Default 9:16.",
      "type": "string",
      "enum": [
        "9:16",
        "1:1",
        "16:9",
        "4:3",
        "3:4"
      ]
    },
    "durationSeconds": {
      "description": "Target clip length; clamped to the model floor of 4s and ceiling of 12s. Default 4.",
      "type": "integer",
      "minimum": 2,
      "maximum": 12
    },
    "polish": {
      "description": "Production polish. `native` = handheld/UGC energy (often wins on Meta); `premium` = cinematic. Default balanced.",
      "type": "string",
      "enum": [
        "native",
        "balanced",
        "premium"
      ]
    },
    "brandProfileId": {
      "description": "Brand profile id to steer tone toward a sub-brand (e.g. Forward / Lux / M Now). Resolved via your workspace brand profiles.",
      "type": "string"
    },
    "model": {
      "description": "Optional video model id override from `lamina_models_list({modality:\"video\"})`.",
      "type": "string",
      "minLength": 1
    },
    "webhookUrl": {
      "description": "Optional HTTPS URL to POST the completion event to.",
      "type": "string",
      "format": "uri"
    }
  },
  "required": [
    "product"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_compose_video

Compose a NARRATED, MULTI-SHOT video from a script — NOT a single ~5s clip. Use this when you need a coherent minute-ish demo / explainer with voiceover: it synthesizes the narration, storyboards it into beats, generates a continuity-chained shot per beat, and renders with transitions + Ken-Burns + captions via Remotion. (For a single short clip, use `lamina_generate_video`.) WORKFLOW: (1) `lamina_compose_video({ script })` → dispatch, get `runId`. (2) `lamina_compose_video({ runId, wait: true })` → block until done; or poll `{ runId }`. Composition takes minutes. INPUTS: • `script` (required to start): the narration to speak (a hook + one insight + a CTA; ≤~90s). The transcript/chapters derive from this, so the video stays coherent with its text. • `title` / `generationBrief` (optional): title + a one-paragraph visual brief for the shots. • `direction` (optional): free-text creative direction ("open on the product, fast cuts, end on the logo") — steer the render WITHOUT naming models. • `sections` (optional): structured per-span hints `[{ text?, hint, mustShow? }]` for a prescriptive storyboard. • `format` / `inputs` (optional): pick a format (else auto-routed); `inputs` supplies a format's required assets (e.g. `{ presenterImage }`). • `aspectRatio` (optional): `16:9` | `9:16` | `1:1` | `4:5` | `4:3` (default 16:9). • `voiceId` (optional): ElevenLabs voice id. Omit and the narration director picks a voice whose tone fits the script. • `expressive` (optional): true → adds v3 audio tags for stronger, more human inflection. (Prosody/pacing is always applied.) • `idempotencyKey` (optional): dedupe retries — the same key returns the same run (no double charge). • `runId` (+ optional `wait`): pass a prior runId to poll instead of starting a new run. TIP: call `lamina_compose_plan({ script })` first to preview the format + cost + storyboard for free before committing. RESPONSE: dispatch → `{ runId, status: "running" }`. Poll → `{ status, progress: { stage, current?, total? } }`. Terminal → `{ status: "completed", result: { videoUrl, durationSeconds, shotCount } }` or `{ status: "failed", error }`. Invalid input → an error with a machine-readable `reason` (e.g. `MISSING_REQUIRED_INPUT`, `SCRIPT_TOO_LONG`).

Parameters14

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
script	string	optional	Narration to speak (≤~90s). Required to start a new run.
title	string	optional	Video title.
generationBrief	string	optional	One-paragraph visual brief for the shots.
direction	string	optional	Free-text creative direction — steer the render without naming models.
sections	array	optional	Structured per-span storyboard hints.
aspectRatio	string	optional
voiceId	string	optional	ElevenLabs voice id. Omit to let the narration director pick a voice by tone.
expressive	boolean	optional	Add v3 audio tags for stronger, more human inflection (default off).
format	string	optional	Render format id (call `lamina_compose_formats` for the menu + costs). Omit to auto-route from the script.
inputs	object	optional	A format's required inputs, e.g. { presenterImage: 'https://…' }.
idempotencyKey	string	optional	Dedupe retries — same key returns the same run.
runId	string	optional	Poll an existing compose run instead of starting a new one.
wait	boolean	optional	When set, block until the run reaches a terminal state.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "script": {
      "description": "Narration to speak (≤~90s). Required to start a new run.",
      "type": "string",
      "maxLength": 4000
    },
    "title": {
      "description": "Video title.",
      "type": "string"
    },
    "generationBrief": {
      "description": "One-paragraph visual brief for the shots.",
      "type": "string",
      "maxLength": 2000
    },
    "direction": {
      "description": "Free-text creative direction — steer the render without naming models.",
      "type": "string",
      "maxLength": 2000
    },
    "sections": {
      "description": "Structured per-span storyboard hints.",
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "text": {
            "description": "The span of narration this hint applies to.",
            "type": "string"
          },
          "hint": {
            "type": "string",
            "description": "What to show / how to treat this span."
          },
          "mustShow": {
            "description": "Hard requirement for this beat.",
            "type": "boolean"
          }
        },
        "required": [
          "hint"
        ]
      }
    },
    "aspectRatio": {
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1",
        "4:5",
        "4:3"
      ]
    },
    "voiceId": {
      "description": "ElevenLabs voice id. Omit to let the narration director pick a voice by tone.",
      "type": "string"
    },
    "expressive": {
      "description": "Add v3 audio tags for stronger, more human inflection (default off).",
      "type": "boolean"
    },
    "format": {
      "description": "Render format id (call `lamina_compose_formats` for the menu + costs). Omit to auto-route from the script.",
      "type": "string"
    },
    "inputs": {
      "description": "A format's required inputs, e.g. { presenterImage: 'https://…' }.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "idempotencyKey": {
      "description": "Dedupe retries — same key returns the same run.",
      "type": "string"
    },
    "runId": {
      "description": "Poll an existing compose run instead of starting a new one.",
      "type": "string"
    },
    "wait": {
      "description": "When set, block until the run reaches a terminal state.",
      "type": "boolean"
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_compose_formats

List the video FORMATS `lamina_compose_video` can render — e.g. animated slideshow, cinematic b-roll, motion-graphics explainer, talking head, picture-in-picture. Each renders differently and internally uses different models; the user picks a FORMAT (never a model) and sees its cost. RESPONSE: `{ formats: [{ id, label, description, available, costTier, estimatedCredits, trending, tags, inputs, previewUrl, thumbnailUrl }], capabilities: { maxScriptDurationSec, aspectRatios, clipSeconds, … } }`. Pass a chosen `id` as `format` to `lamina_compose_video`; supply a format's `inputs` when it lists required ones. `available: false` entries are on the roadmap and cannot be dispatched yet. Optional `durationSeconds` scales the cost estimate.

Parameters2

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
durationSeconds	integer	optional	Target length for the cost estimate (default 60).

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "durationSeconds": {
      "description": "Target length for the cost estimate (default 60).",
      "type": "integer",
      "minimum": 5,
      "maximum": 600
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_compose_plan

PREVIEW what `lamina_compose_video` will do for a script — the format it routes to, the estimated cost, and the per-beat storyboard — WITHOUT generating anything or spending a credit. Fast (one LLM call). Call this first to show the user the plan + cost and confirm before committing. RESPONSE: `{ ready, format: { id, label, reason }, cost: { tier, estimatedCredits }, estimatedDurationSec, beatCount, beats: [{ treatment, effect, transition, imagePrompt }], missingInputs }`. `ready: false` + `missingInputs`/`blockers` tell you exactly what to supply before dispatching. Accepts the same steering inputs as `lamina_compose_video` (`script`, `format`, `direction`, `sections`, `inputs`, `aspectRatio`).

Parameters8

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
script	string	required	Narration to preview a plan for.
generationBrief	string	optional
direction	string	optional	Free-text creative direction.
sections	array	optional
format	string	optional	Preview a specific format (else auto-routed).
inputs	object	optional	A format's required inputs.
aspectRatio	string	optional

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "script": {
      "type": "string",
      "maxLength": 4000,
      "description": "Narration to preview a plan for."
    },
    "generationBrief": {
      "type": "string",
      "maxLength": 2000
    },
    "direction": {
      "description": "Free-text creative direction.",
      "type": "string",
      "maxLength": 2000
    },
    "sections": {
      "type": "array",
      "items": {
        "type": "object",
        "properties": {
          "text": {
            "type": "string"
          },
          "hint": {
            "type": "string"
          },
          "mustShow": {
            "type": "boolean"
          }
        },
        "required": [
          "hint"
        ]
      }
    },
    "format": {
      "description": "Preview a specific format (else auto-routed).",
      "type": "string"
    },
    "inputs": {
      "description": "A format's required inputs.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "aspectRatio": {
      "type": "string",
      "enum": [
        "16:9",
        "9:16",
        "1:1",
        "4:5",
        "4:3"
      ]
    }
  },
  "required": [
    "script"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_brand

Load the brand context the user has configured for this workspace — voice, visual identity, guardrails, prompt directives, performance patterns. Call this when the user mentions branding, voice, or guardrails, or when you want to weave brand-aware language into `inputs` for `lamina_run`. Returns three independent sections (each can be `null` or empty): - `brandDna` — voice, visual identity, content pillars, audience signals, guardrails. Populated when the workspace has both a brand profile filled in AND brand-DNA synthesis has run. - `guidance` — workflow-scoped prompt directives, negative prompts, recommended moves. Populated by content scoring / recommendation jobs. - `topPatterns` — top-performing patterns aggregated from this workspace's run history. Populated by content scoring runs (look at `topPatterns.itemCount` — `0` means no scored content yet). If a section is `null` (or `topPatterns.itemCount === 0`), the user hasn't configured that piece yet. **Do not fabricate brand attributes.** Tell the user honestly: "I don't see a brand profile / content history configured for your workspace — you can add one in your Lamina workspace settings to get brand-aware suggestions. For now I'll proceed with what you've supplied directly." Then continue with the task using only the user's stated inputs. When sections are populated, fold the relevant strings into the `inputs` you build for `lamina_run` — voice cues into text fields, guardrails into negative prompts, winning patterns as suggestions you can offer the user.

Parameters8

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
brandProfileId	string	optional	Specific brand profile to inspect.
campaignId	string	optional	Campaign to scope guidance to.
workflowId	string	optional	Workflow/app to scope guidance to.
platform	string	optional	Target platform for guidance.
objective	string	optional	Content objective, such as engagement or sales.
modality	string	optional	Content modality, such as image or video.
topK	integer	optional	Pattern count.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "brandProfileId": {
      "description": "Specific brand profile to inspect.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "campaignId": {
      "description": "Campaign to scope guidance to.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "workflowId": {
      "description": "Workflow/app to scope guidance to.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "platform": {
      "description": "Target platform for guidance.",
      "type": "string"
    },
    "objective": {
      "description": "Content objective, such as engagement or sales.",
      "type": "string"
    },
    "modality": {
      "description": "Content modality, such as image or video.",
      "type": "string"
    },
    "topK": {
      "default": 10,
      "description": "Pattern count.",
      "type": "integer",
      "minimum": 1,
      "maximum": 50
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_upload_asset

Get a pre-signed upload URL for one user-supplied asset (image, video, or audio). Use this when the user provides a local file you need to feed into `lamina_run` (or `lamina_create.inputs`) as a URL parameter (e.g. `your_photo_image_url`, `product_image_url`, `brand_logo_url`). How to use: - Pass `filename` (the name to register, e.g. "selfie.jpg") and `mediaType` ("image" | "video" | "audio"). - This tool returns `{ uploadUrl, assetUrl, contentTypeHint }`. The `uploadUrl` is a pre-signed PUT URL; the `assetUrl` is what you eventually pass to `lamina_run` (or pre-supply in `lamina_create.inputs`). - THE BYTES DO NOT GO THROUGH THIS TOOL CALL. After this returns, perform an HTTP PUT of the file bytes directly to `uploadUrl` with the `Content-Type` header set to `contentTypeHint` (or override). When the PUT completes (200), the asset is live at `assetUrl`. If your host has shell access (Claude Code, Cursor): execute `curl -X PUT --data-binary @<local-path> -H 'Content-Type: <contentTypeHint>' '<uploadUrl>'` to upload, then call `lamina_run` with `assetUrl` in the relevant input (or pre-supply it to `lamina_create.inputs` so the router doesn't re-ask). If your host doesn't have shell access (Claude Desktop, Claude.ai, ChatGPT): tell the user honestly that you cannot move the bytes from your context to Lamina's storage, and ask them to provide a publicly-reachable URL of the asset (or upload via the Lamina CLI / SDK from a shell), then continue with that URL. Asset URLs returned here are stable and can be reused across multiple runs. There is no need to re-upload between dispatches of related runs.

Parameters3

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
filename	string	required	Filename to register, including extension (e.g. "selfie.jpg").
mediaType	string	required	Media kind. Picks the upload bucket; the actual MIME type is set on PUT.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "filename": {
      "type": "string",
      "minLength": 1,
      "maxLength": 256,
      "description": "Filename to register, including extension (e.g. \"selfie.jpg\")."
    },
    "mediaType": {
      "type": "string",
      "enum": [
        "image",
        "video",
        "audio"
      ],
      "description": "Media kind. Picks the upload bucket; the actual MIME type is set on PUT."
    }
  },
  "required": [
    "filename",
    "mediaType"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_cancel

Cancel a queued or running execution by `runId`. Idempotent — if the run already reached a terminal state (completed / failed / cancelled), the server returns its current status without erroring. Use this when the user changes their mind mid-flight (wrong inputs after dispatch, oversized variant set, abandoned long-running job). Stopping `lamina_status` polls does NOT cancel a run — the orchestrator keeps spending credits until the workflow terminates on its own.

Parameters2

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
runId	string	required	Run ID returned by `lamina_run`.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "runId": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "Run ID returned by `lamina_run`."
    }
  },
  "required": [
    "runId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_create

Plan a creative run from a free-text brief. The router agent searches the catalog, picks the best-fit app by CAPABILITY ENVELOPE (an app whose `outputs[]` can deliver the brief, even when broader than asked — narrow via output selection), drafts inputs from the brief, and surfaces every choice the human still needs to make. NEVER dispatches a run — that's `lamina_run`'s job. Branch on `data.status`: • `"plan"` (mode `"app"`): the router committed to an app. Response includes `selectedApp.appId`, `draftedInputs`, optional `selectedOutputs` (output-label subset), and `askUser[]` (per-parameter questions the human must answer). The `askUser` list is the WORKHORSE — it covers everything the human needs to decide on the chosen app: USER-OWNED slots (product photo, brand logo, headshot), PRESET option picks (background style, aesthetic, mood-board references — curated option labels are listed INLINE in the question text), output subsetting (when the entry is `{ name: "__outputs", question }`, the answer is a comma-separated list of output labels), and any KNOB the user needs to choose. To dispatch: ask the human each `askUser[i].question` in chat, collect answers, then call `lamina_run` with `appId: selectedApp.appId`, `inputs: {…draftedInputs, …<answers keyed by askUser[i].name>}`, and `outputs: <selectedOutputs OR the labels parsed from the __outputs answer>`. ONE dispatch round. • `"needs_clarification"`: the router could not commit to an app because the brief is genuinely ambiguous between two or more apps (e.g. banner vs. reel vs. video, single hero vs. multi-language adapts). This is PRE-COMMIT ROUTING ambiguity only. Response includes `clarifications: [{ question }]`. Ask the human each clarification, fold the answers into a refined brief, then call `lamina_create` again. This is the ONLY status where re-calling `lamina_create` with a refined brief is correct. • `"unmatched"`: no pre-built app fits. Response includes `reason`, and — when the brief is a buildable creative request (no catalog app matched) — a `suggestion` object `{ tool: "lamina_generate_workflow", instruction }`. If `suggestion` is present, offer to BUILD a bespoke app: call `lamina_generate_workflow` with the given `instruction`, then `lamina_run` the returned `appId`. If there is no `suggestion`, the brief is outside Lamina's creative-media surface — tell the human and do not retry. ANTI-DRIFT: After `lamina_create` returns `"plan"`, NEVER re-call `lamina_create` to resolve `askUser` items — that re-rolls the LLM and may pick a different app or drop the partial plan. Resolve asks via `lamina_run` with the answers folded into `inputs`/`outputs`. Re-calling `lamina_create` is ONLY correct when the prior response was `"needs_clarification"`, in which case fold the human's clarification answers into a REFINED BRIEF and call `lamina_create` again. The user has NO form UI — they only see what you (the calling LLM) tell them in chat. Treat every `askUser` entry as a question to surface to the human verbatim, including the inline option lists for PRESET choices (so the human knows what they can pick) and the output labels for `__outputs` asks (so they know which deliverables are available). The router never silently uses demo defaults on user-owned slots — that's why those slots appear in `askUser`. Always collect answers first, then dispatch via `lamina_run`.

Parameters7

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
brief	string	required	The user's natural-language request (e.g. "selfie with Tom Holland", "moody dawn product shot for our skincare line").
modality	string	optional	Optional output modality hint when known. Improves app routing precision.
platform	string	optional	Optional target platform hint (instagram, tiktok, web, etc.). Used for aspect-ratio + framing decisions.
appId	string	optional	Optional pin: skip app discovery and force the router to use this app. Useful when the user already chose an app earlier in the conversation.
inputs	object	optional	Optional pre-supplied inputs keyed by parameter `key`. Anything the user already gave you can go here so the router doesn't ask for it again.
numVariants	integer	optional	Optional variant count hint when the user asked for multiple outputs.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "brief": {
      "type": "string",
      "minLength": 1,
      "description": "The user's natural-language request (e.g. \"selfie with Tom Holland\", \"moody dawn product shot for our skincare line\")."
    },
    "modality": {
      "description": "Optional output modality hint when known. Improves app routing precision.",
      "type": "string",
      "enum": [
        "image",
        "video"
      ]
    },
    "platform": {
      "description": "Optional target platform hint (instagram, tiktok, web, etc.). Used for aspect-ratio + framing decisions.",
      "type": "string"
    },
    "appId": {
      "description": "Optional pin: skip app discovery and force the router to use this app. Useful when the user already chose an app earlier in the conversation.",
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$"
    },
    "inputs": {
      "description": "Optional pre-supplied inputs keyed by parameter `key`. Anything the user already gave you can go here so the router doesn't ask for it again.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    },
    "numVariants": {
      "description": "Optional variant count hint when the user asked for multiple outputs.",
      "type": "integer",
      "minimum": 1,
      "maximum": 20
    }
  },
  "required": [
    "brief"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_generate_workflow

Generate a BRAND-NEW Lamina app from a plain-language instruction, OR EDIT an existing generated app in place. Use this when NO existing app fits the goal (check `lamina_discover` first) and the user wants a bespoke workflow — or when a follow-up needs the app itself changed (add a step, new output, swap a model), not just a different run. A headless Claude planner assembles a validated node graph from the Lamina node catalog and auto-publishes it as a PRIVATE, immediately-runnable app. - `instruction`: describe what the app should create (or, in edit mode, the change to make), including the inputs the user will provide and the desired output(s). - `baseAppId` (optional): EDIT MODE. The appId of a generated app to modify. The planner starts from its current graph and applies `instruction` as a targeted edit — keeping everything it does not touch — then updates that SAME app in place (same appId, run history preserved). Requires you to be the app creator or a workspace owner/admin. Omit to build a new app. - `ops` (optional, EDIT MODE — the CHEAP path): when you already know the exact change and can express it as a small op list, pass `ops` instead of `instruction` — the server applies them deterministically with NO planner LLM call and no credit charge. Each op is one of: `{op:"setNodeData",nodeId,data}`, `{op:"addNode",node:{id,type,data?}}`, `{op:"removeNode",nodeId}`, `{op:"addEdge",edge:{source,target,sourceHandle?,targetHandle?}}`, `{op:"removeEdge",source,target}`, `{op:"addParameter",parameter:{key,name,type,targetNodeId,targetField,...}}`, `{op:"removeParameter",key}`, `{op:"setParameter",key,patch}`. Requires `baseAppId`. Read the app first (`lamina_describe`/`GET /v1/apps/{id}`) to get node ids. Use `instruction` (planner) for anything you cannot express as ops. - `name` (optional): preferred app name. - `visibility` (optional): `private` (default), `shared` (whole workspace), or `public`. Ignored in edit mode. - `brandProfileId` (optional): bake a brand's voice/visual/guardrails into the app so it's on-brand by default. Omit to use the workspace's active brand. - Returns `{ appId, name, parameters[], outputs[], runUrl }`. In edit mode `appId` is unchanged. Feed `appId` + the returned parameter `key`s straight into `lamina_run` — the parameter set may have changed, so re-read `parameters[]`. - On failure returns `{ error, details[] }` where details are the validation problems the planner could not resolve.

Parameters10

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
instruction	string	optional	Plain-language description of the app to build — or, with baseAppId, the change to apply. Optional only when `ops` is provided.
baseAppId	string	optional	Edit an existing generated app in place. Its appId. Omit to build a new app.
ops	array	optional	EDIT MODE cheap path: explicit edit operations applied deterministically (no planner LLM). Requires baseAppId. See the tool description for op shapes.
name	string	optional	Optional preferred app name.
visibility	string	optional	App reach after creation. Defaults to private.
provider	string	optional	Planner LLM provider. Defaults to the server setting (claude).
brandProfileId	string	optional	Bake a specific brand profile's voice, visual anchors, and guardrails into the generated app so it produces on-brand output. Defaults to the workspace's active brand.
run	boolean	optional	One-shot: after generating, immediately run the app with `inputs`. Returns the started runId — check with lamina_status.
inputs	object	optional	Input values keyed by the generated app parameter `key` (media as URLs). Used only when run is true.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "instruction": {
      "description": "Plain-language description of the app to build — or, with baseAppId, the change to apply. Optional only when `ops` is provided.",
      "type": "string"
    },
    "baseAppId": {
      "description": "Edit an existing generated app in place. Its appId. Omit to build a new app.",
      "type": "string"
    },
    "ops": {
      "description": "EDIT MODE cheap path: explicit edit operations applied deterministically (no planner LLM). Requires baseAppId. See the tool description for op shapes.",
      "type": "array",
      "items": {
        "type": "object",
        "propertyNames": {
          "type": "string"
        },
        "additionalProperties": {}
      }
    },
    "name": {
      "description": "Optional preferred app name.",
      "type": "string"
    },
    "visibility": {
      "description": "App reach after creation. Defaults to private.",
      "type": "string",
      "enum": [
        "private",
        "shared",
        "public"
      ]
    },
    "provider": {
      "description": "Planner LLM provider. Defaults to the server setting (claude).",
      "type": "string",
      "enum": [
        "claude",
        "openai"
      ]
    },
    "brandProfileId": {
      "description": "Bake a specific brand profile's voice, visual anchors, and guardrails into the generated app so it produces on-brand output. Defaults to the workspace's active brand.",
      "type": "string"
    },
    "run": {
      "description": "One-shot: after generating, immediately run the app with `inputs`. Returns the started runId — check with lamina_status.",
      "type": "boolean"
    },
    "inputs": {
      "description": "Input values keyed by the generated app parameter `key` (media as URLs). Used only when run is true.",
      "type": "object",
      "propertyNames": {
        "type": "string"
      },
      "additionalProperties": {}
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_app_versions

List a generated app's saved graph versions, or restore it to one. Every `lamina_generate_workflow` edit snapshots the app's prior graph first, so a bad edit is always recoverable. - `appId` (required): the generated app. - Omit `restore` to LIST versions — returns `{ versions: [{ version, createdAt, createdBy, changeSummary }] }`, newest first. - Pass `restore: <version>` to RESTORE that version — swaps its graph + parameters back in (the current graph is snapshotted first, so restore is itself undoable). Returns `{ appId, restoredFrom, newVersion }`. Requires you to be the app creator or a workspace owner/admin.

Parameters3

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
appId	string	required	The generated app to inspect or restore.
restore	integer	optional	A version number to restore (from the list). Omit to just list versions.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "appId": {
      "type": "string",
      "description": "The generated app to inspect or restore."
    },
    "restore": {
      "description": "A version number to restore (from the list). Omit to just list versions.",
      "type": "integer",
      "minimum": 1,
      "maximum": 9007199254740991
    }
  },
  "required": [
    "appId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_set_visibility

Change an app's reach: `private` (creator/workspace-owner only), `shared` (any workspace member — discoverable via `lamina_discover`), or `public`. Only the app creator or a workspace owner may change visibility. Useful right after `lamina_generate_workflow` to share a freshly generated app.

Parameters3

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
appId	string	required	App ID to update.
visibility	string	required	New reach for the app.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "appId": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "App ID to update."
    },
    "visibility": {
      "type": "string",
      "enum": [
        "private",
        "shared",
        "public"
      ],
      "description": "New reach for the app."
    }
  },
  "required": [
    "appId",
    "visibility"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_set_brand

Create or update this workspace's brand and ground it with a starter Brand DNA, so generated apps and `applyBrand` runs produce on-brand output. Use it to make a fresh workspace on-brand before generating. - `brandName` (required): the brand to create, or the display name when updating. - `brandProfileId` (optional): update an existing profile instead of creating one. Omit to create. - `guardrails` (optional): things to avoid — these become the brand's negatives on visual generation. - `brandVoice` / `visualStyle` / `targetAudience` / `description` / `industry` (optional): shape the brand. - Returns `{ brandProfileId, reused }`. Pass that `brandProfileId` to `lamina_generate_workflow` or `lamina_run` (with `applyBrand`). - Requires an owner/admin identity. Read the current brand with `lamina_brand`.

Parameters9

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
brandName	string	required	Brand to create, or display name when updating.
brandProfileId	string	optional	Update this existing profile. Omit to create a new one.
guardrails	array	optional	Things to avoid — become the brand's visual negatives.
brandVoice	string	optional	Tone/voice, e.g. "warm, confident, never salesy".
visualStyle	string	optional	Visual anchors, e.g. "clean studio lighting, muted palette".
targetAudience	string	optional	Who the brand speaks to.
description	string	optional	Short description of the brand.
industry	string	optional	Industry / vertical.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "brandName": {
      "type": "string",
      "minLength": 1,
      "description": "Brand to create, or display name when updating."
    },
    "brandProfileId": {
      "description": "Update this existing profile. Omit to create a new one.",
      "type": "string"
    },
    "guardrails": {
      "description": "Things to avoid — become the brand's visual negatives.",
      "type": "array",
      "items": {
        "type": "string"
      }
    },
    "brandVoice": {
      "description": "Tone/voice, e.g. \"warm, confident, never salesy\".",
      "type": "string"
    },
    "visualStyle": {
      "description": "Visual anchors, e.g. \"clean studio lighting, muted palette\".",
      "type": "string"
    },
    "targetAudience": {
      "description": "Who the brand speaks to.",
      "type": "string"
    },
    "description": {
      "description": "Short description of the brand.",
      "type": "string"
    },
    "industry": {
      "description": "Industry / vertical.",
      "type": "string"
    }
  },
  "required": [
    "brandName"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_brand_feedback

Give an on/off-brand verdict on a completed run, closing the loop so the next generation respects it. A `reject` with a `note` turns the reason into a brand guardrail — which then flows into `lamina_generate_workflow` and `applyBrand` runs as a negative, so the same off-brand result is avoided. `approve` is acknowledged without changing the brand. - `runId` (required): a run you started (from `lamina_run` / `lamina_status`). - `verdict` (required): `approve` or `reject`. - `note` (optional but recommended on reject): why it is off-brand — this becomes the guardrail. - `brandProfileId` (optional): target brand. Defaults to the run's app brand. - Returns `{ brandProfileId, verdict, applied, guardrails }`. Requires an owner/admin identity.

Parameters5

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
runId	string	required	Run to give feedback on.
verdict	string	required	Whether the output is on-brand.
note	string	optional	Why it is off-brand — becomes a brand guardrail when verdict is reject.
brandProfileId	string	optional	Target brand. Defaults to the run's app brand.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "runId": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "Run to give feedback on."
    },
    "verdict": {
      "type": "string",
      "enum": [
        "approve",
        "reject"
      ],
      "description": "Whether the output is on-brand."
    },
    "note": {
      "description": "Why it is off-brand — becomes a brand guardrail when verdict is reject.",
      "type": "string"
    },
    "brandProfileId": {
      "description": "Target brand. Defaults to the run's app brand.",
      "type": "string"
    }
  },
  "required": [
    "runId",
    "verdict"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_brand_compliance

Read the Brand Guard result a run recorded — the per-node on/off-brand status and score against the workspace brand. Use it to drive the approve/reject turn: after a run, show the output alongside this compliance read, ask the user to approve or reject, and on a reject call `lamina_brand_feedback` (which turns the reason into a guardrail the next generation avoids). - `runId` (required): a run you started (from `lamina_run` / `lamina_status`). - Returns `{ enabled, brandProfileId, nodes[] }`. Each node has `{ nodeId, status, overallScore, brandDeviations, checkedAt }`. `enabled: false` means Brand Guard was off for that app — use `lamina_brand_score` to score it on demand instead.

Parameters2

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
runId	string	required	Run to read brand compliance for.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "runId": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "Run to read brand compliance for."
    }
  },
  "required": [
    "runId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_brand_score

Score how on-brand a completed run's image output is, and get back the specific deviations — before you show it to the user or decide whether to regenerate. Works on ANY completed run, whether or not Brand Guard was enabled on the app. - `runId` (required): a completed run (from `lamina_run` / `lamina_status`). - `brandProfileId` (optional): brand to score against. Defaults to the run's app brand. - Returns `{ brandFit, dimensions, deviations, suggestions }`. `brandFit` is 0–100; `deviations` lists the specific guideline breaks; `suggestions` is how to fix them. - Use it as the check in a generate → score → refine loop: if `brandFit` is below your bar, feed `deviations`/`suggestions` back into the next generation.

Parameters3

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
runId	string	required	Completed run to score.
brandProfileId	string	optional	Brand to score against. Defaults to the run's app brand.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "runId": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "Completed run to score."
    },
    "brandProfileId": {
      "description": "Brand to score against. Defaults to the run's app brand.",
      "type": "string"
    }
  },
  "required": [
    "runId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_refine_to_brand

Automatically improve a completed run until it's on-brand — without letting it run away on cost. Repeats score → refine (re-rolling with the specific deviations fed back in) and stops the instant the score clears your bar, the iteration cap is hit, or the credit budget would be exceeded — whichever comes first. Returns the best result plus exactly how many iterations and credits it took. - `runId` (required): a completed run to improve. - `minScore` (optional, default 80): stop once `brandFit` reaches this (0–100). - `maxIterations` (optional, default 3): most refine passes to try (1–10). - `maxCredits` (optional, default 200): hard credit ceiling — never exceeded. - `brandProfileId` (optional): brand to score against. Defaults to the run's app brand. - Returns `{ best, iterations, creditsSpent, stoppedBecause, attempts }`. `best.imageUrl` is the highest-scoring result; `stoppedBecause` is `met_score` | `max_iterations` | `budget` | `no_output`.

Parameters6

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
runId	string	required	Completed run to refine toward the brand.
minScore	number	optional	Target brand-fit score to stop at (default 80).
maxIterations	number	optional	Most refine passes to try (default 3).
maxCredits	number	optional	Hard credit ceiling — never exceeded (default 200).
brandProfileId	string	optional	Brand to score against. Defaults to the run's app brand.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "runId": {
      "type": "string",
      "format": "uuid",
      "pattern": "^([0-9a-fA-F]{8}-[0-9a-fA-F]{4}-[1-8][0-9a-fA-F]{3}-[89abAB][0-9a-fA-F]{3}-[0-9a-fA-F]{12}|00000000-0000-0000-0000-000000000000|ffffffff-ffff-ffff-ffff-ffffffffffff)$",
      "description": "Completed run to refine toward the brand."
    },
    "minScore": {
      "description": "Target brand-fit score to stop at (default 80).",
      "type": "number",
      "minimum": 0,
      "maximum": 100
    },
    "maxIterations": {
      "description": "Most refine passes to try (default 3).",
      "type": "number",
      "minimum": 1,
      "maximum": 10
    },
    "maxCredits": {
      "description": "Hard credit ceiling — never exceeded (default 200).",
      "type": "number",
      "minimum": 1,
      "maximum": 100000
    },
    "brandProfileId": {
      "description": "Brand to score against. Defaults to the run's app brand.",
      "type": "string"
    }
  },
  "required": [
    "runId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_credits

Check the workspace's credit balance and the credit packages available to buy — so you can tell the user what they have and what a top-up would cost before running anything expensive. - Returns `{ balance, packages[] }`. Each package has `{ packageId, name, credits, priceCents, currency }`. - To buy one, hand the `packageId` to `lamina_topup`.

Parameters1

apiKey

string

optional

Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    }
  },
  "$schema": "http://json-schema.org/draft-07/schema#"
}

lamina_topup

Start a credit top-up and get back a Stripe-hosted checkout link to give the user. Use this when the balance is too low to run what they asked for — no need to send them to a dashboard. - `packageId` (required): from `lamina_credits`. - Returns `{ checkoutUrl, credits, amountCents, currency }`. Give the user the `checkoutUrl` to pay; once they do, the credits land on the workspace and you can retry the run. - Never ask the user for card details — they pay on the Stripe page the link opens.

Parameters2

apiKey	string	optional	Workspace API key (starts with "lma_"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.
packageId	string	required	Credit package to buy (from `lamina_credits`).

Raw schema

{
  "type": "object",
  "properties": {
    "apiKey": {
      "description": "Workspace API key (starts with \"lma_\"). Only needed when the MCP is NOT OAuth-authorized; when you connect via OAuth the workspace comes from your login and this is ignored.",
      "type": "string",
      "minLength": 1
    },
    "packageId": {
      "type": "string",
      "minLength": 1,
      "description": "Credit package to buy (from `lamina_credits`)."
    }
  },
  "required": [
    "packageId"
  ],
  "$schema": "http://json-schema.org/draft-07/schema#"
}

Install

Tools (27)

lamina_discoverlamina_describelamina_runlamina_statuslamina_models_listlamina_models_describelamina_generate_imagelamina_generate_video

Remote endpoint

Streamable HTTP

Hosted server - connect over the network, no local install.

url

https://app.uselamina.ai/mcp/agent

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "lamina": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://app.uselamina.ai/mcp/agent"
      ]
    }
  }
}

Desktop config is stdio-only; this bridges via mcp-remote. Native remote: Settings > Connectors.

MCP Server: ai.uselamina/lamina

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

lamina_discover

lamina_describe

lamina_run

lamina_status

lamina_models_list

lamina_models_describe

lamina_generate_image

lamina_generate_video

lamina_plv_background

lamina_generate_hook

lamina_compose_video

lamina_compose_formats

lamina_compose_plan

lamina_brand

lamina_upload_asset

lamina_cancel

lamina_create

lamina_generate_workflow

lamina_app_versions

lamina_set_visibility

lamina_set_brand

lamina_brand_feedback

lamina_brand_compliance

lamina_brand_score

lamina_refine_to_brand

lamina_credits

lamina_topup

Install

Remote endpoint

Related servers