Siren

Official21 tools

by Hexahedral-Inc

Deterministic visual marketing engine. Your agent plans, renders, and posts on-brand campaigns.

MCP Server: ai.mysiren/siren

The ai.mysiren/siren MCP server is a deterministic visual marketing engine. It enables an agent to plan, render, and post on-brand campaigns, based on the provided description. The server focuses on producing visual marketing content in a repeatable manner.

🛠️ Key Features

Deterministic visual marketing engine
Agent workflow supports planning
Agent workflow supports rendering
Agent workflow supports posting
Produces on-brand campaigns

🚀 Use Cases

Visual marketing campaign planning
Visual campaign rendering
Publishing on-brand marketing campaigns

⚡ Developer Benefits

Repeatable (deterministic) campaign generation
Single agent-driven pipeline for plan → render → post

⚠️ Limitations

Description does not specify supported platforms, integrations, or configuration options.

Topics

claudecursormarketingmcpmcp-servermodel-context-protocolsocial-media

Captured live from the server via tools/list.

get_account

Get the connected Siren workspace: plan, key scopes, auto-post setting, and daily limit. Call this first to learn what the account can do before generating. Empty asset_types / channels / connected_accounts lists mean UNRESTRICTED, not missing — never stop on them. Film renders need plan pro or above (empire/scale/pro).

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

list_runs

List the workspace's recent generation runs (newest first): status, brief, channel, asset URLs, and audience scores.

Parameters1

limit

integer

optional

How many runs to return, 1 to 50. Newest first.

Raw schema

{
  "type": "object",
  "properties": {
    "limit": {
      "default": 10,
      "description": "How many runs to return, 1 to 50. Newest first.",
      "type": "integer"
    }
  },
  "additionalProperties": false
}

get_run

Get one run by id — full status, output text, asset URLs, impact and audience scores, and any error. Poll this after create_campaign or render_asset until status is terminal. After post_run, `posts[]` carries each platform's status and, once it fires, the live URL and the caption that went out.

Parameters1

run_id

string

required

The run id returned by create_campaign, render_asset, or list_runs.

Raw schema

{
  "type": "object",
  "properties": {
    "run_id": {
      "description": "The run id returned by create_campaign, render_asset, or list_runs.",
      "type": "string"
    }
  },
  "required": [
    "run_id"
  ],
  "additionalProperties": false
}

create_campaign

Create a Siren campaign from a plain-language brief — the full pipeline: plan, on-brand copy, deterministic render, verify. Returns the run; poll get_run until it finishes. Spends credits (image 10, video 25; voice or music-only is the same 25). Pass output_type to pin a film (list_films has the catalog); omit it and Siren picks. Optional scheduled_at (ISO-8601) queues a sequential post (X → Instagram → TikTok, or platforms you pass) when the render succeeds — requires Allow posting. Fails with a 402 upgrade message if the plan or balance can't cover it.

Parameters8

brief	string	required	Plain-language request for the post, e.g. "announce the new export feature, use the dashboard screenshot".
channel	string	optional	Target channel for the render: twitter, instagram, linkedin, tiktok, or youtube. Sets the aspect and copy length.
asset_type	string	optional	What to make: card (still image) or video.
output_type	any	optional	Optional film to pin, e.g. "story" or "pitch". Call list_films to browse; describe_film for the contract. Omit and Siren picks the format from the brief.
caption	any	optional	Optional caption for the post this run becomes. Your words are kept; omit and Siren writes the caption.
scheduled_at	any	optional	ISO-8601 time to post, e.g. 2026-09-12T09:00:00. Interpreted in the given timezone.
timezone	string	optional	IANA timezone name for scheduled_at, e.g. Africa/Lagos or America/New_York.
platforms	any	optional	Where to post: any of x, instagram, tiktok, linkedin, youtube, or ["everything"] for every connected channel.

Raw schema

{
  "type": "object",
  "properties": {
    "brief": {
      "description": "Plain-language request for the post, e.g. \"announce the new export feature, use the dashboard screenshot\".",
      "type": "string"
    },
    "channel": {
      "default": "twitter",
      "description": "Target channel for the render: twitter, instagram, linkedin, tiktok, or youtube. Sets the aspect and copy length.",
      "type": "string"
    },
    "asset_type": {
      "default": "card",
      "description": "What to make: card (still image) or video.",
      "type": "string"
    },
    "output_type": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional film to pin, e.g. \"story\" or \"pitch\". Call list_films to browse; describe_film for the contract. Omit and Siren picks the format from the brief."
    },
    "caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional caption for the post this run becomes. Your words are kept; omit and Siren writes the caption."
    },
    "scheduled_at": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "ISO-8601 time to post, e.g. 2026-09-12T09:00:00. Interpreted in the given timezone."
    },
    "timezone": {
      "default": "UTC",
      "description": "IANA timezone name for scheduled_at, e.g. Africa/Lagos or America/New_York.",
      "type": "string"
    },
    "platforms": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Where to post: any of x, instagram, tiktok, linkedin, youtube, or [\"everything\"] for every connected channel."
    }
  },
  "required": [
    "brief"
  ],
  "additionalProperties": false
}

list_films

Every live film master Siren can render: name, what it is, when to hire it, runtime, aspect, and whether this plan can render it. Films are deterministic MP4s; video renders need Pro or above. Read this before promising a specific film, then describe_film for its body.

Parameters1

goal

any

optional

Optional: the human's own words for the outcome, e.g. "tell our story" or "launch a feature". Reorders the catalog by fit.

Raw schema

{
  "type": "object",
  "properties": {
    "goal": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional: the human's own words for the outcome, e.g. \"tell our story\" or \"launch a feature\". Reorders the catalog by fit."
    }
  },
  "additionalProperties": false
}

describe_film

The full contract for one film: what it is and when to hire it, its body JSON Schema, a reference body, the seed envelope, media slots (which fields take image/video URLs), the brand prefills (colours, logo, screens) and the override rules. Call it before writing a render_asset body.

Parameters1

output_type

string

required

Film id from list_films, e.g. "story", "pitch", "gallery".

Raw schema

{
  "type": "object",
  "properties": {
    "output_type": {
      "description": "Film id from list_films, e.g. \"story\", \"pitch\", \"gallery\".",
      "type": "string"
    }
  },
  "required": [
    "output_type"
  ],
  "additionalProperties": false
}

clarify_brief

Ask Siren's clarifier whether a brief is specific enough to generate from. Returns ready=true/false plus follow-up questions. Use before create_campaign when the user's request is vague.

Parameters1

brief

string

required

Plain-language request for the post, e.g. "announce the new export feature, use the dashboard screenshot".

Raw schema

{
  "type": "object",
  "properties": {
    "brief": {
      "description": "Plain-language request for the post, e.g. \"announce the new export feature, use the dashboard screenshot\".",
      "type": "string"
    }
  },
  "required": [
    "brief"
  ],
  "additionalProperties": false
}

render_asset

Render pre-formed SirenSeed bodies directly (advanced): deterministic template render, no planner. Each item: {output_type, channel, seed_body, archetype?, family?, surface?, caption?, voice_id?}. Prefer create_campaign unless the user has concrete seed JSON. Returns run ids — poll get_run for status.

Parameters2

items	array	required	Pre-formed SirenSeed bodies to render. Each item: {output_type, channel, seed_body, archetype?, family?, surface?, caption?, voice_id?}.
name	any	optional	Human-readable name for the asset or run.

Raw schema

{
  "type": "object",
  "properties": {
    "items": {
      "description": "Pre-formed SirenSeed bodies to render. Each item: {output_type, channel, seed_body, archetype?, family?, surface?, caption?, voice_id?}.",
      "items": {
        "additionalProperties": true,
        "type": "object"
      },
      "type": "array"
    },
    "name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Human-readable name for the asset or run."
    }
  },
  "required": [
    "items"
  ],
  "additionalProperties": false
}

upload_media

Store a photo or video the human wants in a post, from an https URL or base64. Returns a workspace-owned URL to put in any media slot of a film body (describe_film lists the slots) — the renderer reads it directly. Images: PNG/JPG/WebP up to 15 MB. Videos: MP4/MOV/WebM up to 200 MB. The same bytes are stored once (content-hashed).

Parameters4

url	any	optional	Public https URL of the photo or video to store. Pass this or base64.
base64	any	optional	The media bytes as base64, if you have no URL. Pass this or url.
kind	string	optional	auto (default), image, or video. Detected from the bytes when auto.
name	string	optional	Human-readable name for the file.

Raw schema

{
  "type": "object",
  "properties": {
    "url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Public https URL of the photo or video to store. Pass this or base64."
    },
    "base64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The media bytes as base64, if you have no URL. Pass this or url."
    },
    "kind": {
      "default": "auto",
      "description": "auto (default), image, or video. Detected from the bytes when auto.",
      "type": "string"
    },
    "name": {
      "default": "",
      "description": "Human-readable name for the file.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

post_run

Post a finished run's assets to the workspace's CONNECTED SOCIAL ACCOUNT. This is live, public distribution on the customer's channel — always confirm with the user before calling. Only works if the grant was authorised with posting allowed. Pass `caption` to own the words; it goes out verbatim. The call queues the post behind a short publish window (about two minutes, cancellable) rather than firing inline: poll get_run after that and read `posts[].url` for the live permalink and the caption that went out.

Parameters3

run_id	string	required	The run id returned by create_campaign, render_asset, or list_runs.
platform	string	optional	Connected channel to post to: x, instagram, tiktok, linkedin, or youtube.
caption	any	optional	Optional caption for this publish; goes out verbatim. Omit and Siren writes it.

Raw schema

{
  "type": "object",
  "properties": {
    "run_id": {
      "description": "The run id returned by create_campaign, render_asset, or list_runs.",
      "type": "string"
    },
    "platform": {
      "default": "x",
      "description": "Connected channel to post to: x, instagram, tiktok, linkedin, or youtube.",
      "type": "string"
    },
    "caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional caption for this publish; goes out verbatim. Omit and Siren writes it."
    }
  },
  "required": [
    "run_id"
  ],
  "additionalProperties": false
}

schedule_post

Schedule a finished run to post at scheduled_at (ISO-8601). Shows in the customer's local timezone. platforms: x, instagram, tiktok, linkedin, youtube, or everything. Posts fire sequentially. Requires Allow posting. Prefer this over post_run when the user names a time. On create_campaign you can pass scheduled_at instead.

Parameters5

run_id	string	required	The run id returned by create_campaign, render_asset, or list_runs.
scheduled_at	string	required	ISO-8601 time to post, e.g. 2026-09-12T09:00:00. Interpreted in the given timezone.
timezone	string	optional	IANA timezone name for scheduled_at, e.g. Africa/Lagos or America/New_York.
platforms	any	optional	Where to post: any of x, instagram, tiktok, linkedin, youtube, or ["everything"] for every connected channel.
captions	any	optional	Optional caption override per platform, e.g. {"x": "...", "linkedin": "..."}.

Raw schema

{
  "type": "object",
  "properties": {
    "run_id": {
      "description": "The run id returned by create_campaign, render_asset, or list_runs.",
      "type": "string"
    },
    "scheduled_at": {
      "description": "ISO-8601 time to post, e.g. 2026-09-12T09:00:00. Interpreted in the given timezone.",
      "type": "string"
    },
    "timezone": {
      "default": "UTC",
      "description": "IANA timezone name for scheduled_at, e.g. Africa/Lagos or America/New_York.",
      "type": "string"
    },
    "platforms": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Where to post: any of x, instagram, tiktok, linkedin, youtube, or [\"everything\"] for every connected channel."
    },
    "captions": {
      "anyOf": [
        {
          "additionalProperties": {
            "type": "string"
          },
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional caption override per platform, e.g. {\"x\": \"...\", \"linkedin\": \"...\"}."
    }
  },
  "required": [
    "run_id",
    "scheduled_at"
  ],
  "additionalProperties": false
}

get_brand_dna

Get this workspace's Brand DNA: name, overview, tagline, offer, features, products, audience, palette, logos. Not Brand Memory.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

update_brand_dna

Patch Brand DNA. Send only keys to change. Nested bags (offer, product_map, icp) merge. Examples: {tagline, overview, offer: {product_name, one_liner, features, who_its_for, primary_cta}, product_map: {offerings, how_we_work}, icp: {who_buys, pains}}. Does not read or write Brand Memory.

Parameters1

fields

object

required

Brand DNA keys to change, e.g. {"tagline": "...", "offer": {"one_liner": "..."}}. Nested bags merge.

Raw schema

{
  "type": "object",
  "properties": {
    "fields": {
      "additionalProperties": true,
      "description": "Brand DNA keys to change, e.g. {\"tagline\": \"...\", \"offer\": {\"one_liner\": \"...\"}}. Nested bags merge.",
      "type": "object"
    }
  },
  "required": [
    "fields"
  ],
  "additionalProperties": false
}

list_product_screens

List the brand assets in Brand DNA: product photos, app screenshots, packaging. Each row has name, kind, description, use_when, tags, scan_status (scanning / ready / failed), device, theme, url.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

upload_product_screen

Upload a brand asset (product photo, app screenshot, packaging) into Brand DNA and store it on R2. Pass image_url (https PNG/JPG/WebP) or image_base64. Two ways to file it: - Send `description` (and optionally kind, use_when, tags, name): Siren trusts your words and files the asset as-is. No read. - Send only the file: Gemini reads the picture and writes name, kind, description, use_when, tags itself. scan_status goes scanning → ready in about 8 seconds; poll list_product_screens. kind is free text ("product photo", "dashboard screenshot", "packaging"), there is no fixed list. A brief that names an asset ("advertise the pink handbag") pulls that file into the still. screen_type / device / theme only matter for device-framed screenshot masters.

Parameters10

image_url	any	optional	Public https URL of a PNG, JPG, or WebP to store as a brand asset.
image_base64	any	optional	The image bytes as base64, if you have no URL.
name	string	optional	Human-readable name for the asset or run.
description	any	optional	What the picture shows and what it is for, in your words. When set, Siren files the asset without reading it.
kind	any	optional	Free-text kind: product photo, dashboard screenshot, packaging, logo, team photo.
use_when	any	optional	When Siren should reach for this asset, e.g. "any post about the analytics page".
tags	any	optional	Short lowercase tags for search, e.g. ["dashboard", "dark-mode"].
screen_type	string	optional	Screen role: feature, hero, onboarding, settings, or marketing.
device	string	optional	Device the screenshot was taken on: phone, tablet, desktop, or none.
theme	string	optional	UI theme in the screenshot: light, dark, or unknown.

Raw schema

{
  "type": "object",
  "properties": {
    "image_url": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Public https URL of a PNG, JPG, or WebP to store as a brand asset."
    },
    "image_base64": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "The image bytes as base64, if you have no URL."
    },
    "name": {
      "default": "",
      "description": "Human-readable name for the asset or run.",
      "type": "string"
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "What the picture shows and what it is for, in your words. When set, Siren files the asset without reading it."
    },
    "kind": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Free-text kind: product photo, dashboard screenshot, packaging, logo, team photo."
    },
    "use_when": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "When Siren should reach for this asset, e.g. \"any post about the analytics page\"."
    },
    "tags": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Short lowercase tags for search, e.g. [\"dashboard\", \"dark-mode\"]."
    },
    "screen_type": {
      "default": "feature",
      "description": "Screen role: feature, hero, onboarding, settings, or marketing.",
      "type": "string"
    },
    "device": {
      "default": "phone",
      "description": "Device the screenshot was taken on: phone, tablet, desktop, or none.",
      "type": "string"
    },
    "theme": {
      "default": "unknown",
      "description": "UI theme in the screenshot: light, dark, or unknown.",
      "type": "string"
    }
  },
  "additionalProperties": false
}

update_product_screen

Edit an existing brand asset: name, description, kind, use_when, and the screenshot tags (screen_type, device, theme).

Parameters8

screen_id	string	required	Id of the brand asset from list_product_screens.
name	any	optional	Human-readable name for the asset or run.
description	any	optional	What the picture shows and what it is for, in your words. When set, Siren files the asset without reading it.
kind	any	optional	Free-text kind: product photo, dashboard screenshot, packaging, logo, team photo.
use_when	any	optional	When Siren should reach for this asset, e.g. "any post about the analytics page".
screen_type	any	optional	Screen role: feature, hero, onboarding, settings, or marketing.
device	any	optional	Device the screenshot was taken on: phone, tablet, desktop, or none.
theme	any	optional	UI theme in the screenshot: light, dark, or unknown.

Raw schema

{
  "type": "object",
  "properties": {
    "screen_id": {
      "description": "Id of the brand asset from list_product_screens.",
      "type": "string"
    },
    "name": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Human-readable name for the asset or run."
    },
    "description": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "What the picture shows and what it is for, in your words. When set, Siren files the asset without reading it."
    },
    "kind": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Free-text kind: product photo, dashboard screenshot, packaging, logo, team photo."
    },
    "use_when": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "When Siren should reach for this asset, e.g. \"any post about the analytics page\"."
    },
    "screen_type": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Screen role: feature, hero, onboarding, settings, or marketing."
    },
    "device": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Device the screenshot was taken on: phone, tablet, desktop, or none."
    },
    "theme": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "UI theme in the screenshot: light, dark, or unknown."
    }
  },
  "required": [
    "screen_id"
  ],
  "additionalProperties": false
}

delete_product_screen

Remove a product screenshot from Brand DNA. Does not delete Brand Memory.

Parameters1

screen_id

string

required

Id of the brand asset from list_product_screens.

Raw schema

{
  "type": "object",
  "properties": {
    "screen_id": {
      "description": "Id of the brand asset from list_product_screens.",
      "type": "string"
    }
  },
  "required": [
    "screen_id"
  ],
  "additionalProperties": false
}

studio_templates

List Siren Studio's 33 React data-card types with family, description, and body schema. Use this before studio_card so the body matches.

Parameters

No parameters.

Raw schema

{
  "type": "object",
  "properties": {},
  "additionalProperties": false
}

studio_card

Render a Studio data card from a type + body. Deterministic React, no paint. Optional live post after render. Returns run_id, image url, and post url when posted.

Parameters8

output_type	string	required	One of the 33 Studio types from studio_templates, e.g. sale-notification.
body	object	required	Card fields for that type (amount, productName, …).
theme	any	optional	dark or light. Omit to use the workspace default.
accent	any	optional	Hex accent, e.g. #5B82FF.
aspect	any	optional	Canvas aspect, e.g. square-ig or wide-twitter.
post	boolean	optional	If true, post the finished card to a connected account. Confirm with the user first.
caption	any	optional	Caption when posting.
platform	string	optional	Connected channel if post is true: x, instagram, tiktok, linkedin, or youtube.

Raw schema

{
  "type": "object",
  "properties": {
    "output_type": {
      "description": "One of the 33 Studio types from studio_templates, e.g. sale-notification.",
      "type": "string"
    },
    "body": {
      "additionalProperties": true,
      "description": "Card fields for that type (amount, productName, …).",
      "type": "object"
    },
    "theme": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "dark or light. Omit to use the workspace default."
    },
    "accent": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Hex accent, e.g. #5B82FF."
    },
    "aspect": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Canvas aspect, e.g. square-ig or wide-twitter."
    },
    "post": {
      "default": false,
      "description": "If true, post the finished card to a connected account. Confirm with the user first.",
      "type": "boolean"
    },
    "caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Caption when posting."
    },
    "platform": {
      "default": "x",
      "description": "Connected channel if post is true: x, instagram, tiktok, linkedin, or youtube.",
      "type": "string"
    }
  },
  "required": [
    "output_type",
    "body"
  ],
  "additionalProperties": false
}

studio_automate

Create a Studio profile on this API key. Returns generate curl and inbound hook URLs (Stripe, GitHub, Uptime Kuma, Product Hunt, generic). Passing delivery.social_account_ids turns on social delivery for the profile — that publishes, so it requires Allow posting.

Parameters4

name	string	required	Name for this automation profile.
output_types	array	required	Studio types this profile may render.
delivery	any	optional	Optional delivery: {social_account_ids?, telegram?, discord?}.
caption	any	optional	Default caption for auto-posted cards.

Raw schema

{
  "type": "object",
  "properties": {
    "name": {
      "description": "Name for this automation profile.",
      "type": "string"
    },
    "output_types": {
      "description": "Studio types this profile may render.",
      "items": {
        "type": "string"
      },
      "type": "array"
    },
    "delivery": {
      "anyOf": [
        {
          "additionalProperties": true,
          "type": "object"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Optional delivery: {social_account_ids?, telegram?, discord?}."
    },
    "caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Default caption for auto-posted cards."
    }
  },
  "required": [
    "name",
    "output_types"
  ],
  "additionalProperties": false
}

studio_schedule

Render a Studio card then queue a ScheduledPost at scheduled_at.

Parameters6

output_type	string	required	Studio type to render.
body	object	required	Card fields for that type.
scheduled_at	string	required	ISO-8601 time to post.
platforms	any	optional	x, instagram, tiktok, linkedin, youtube, or everything.
caption	any	optional	Caption for the scheduled post.
timezone	string	optional	IANA timezone for scheduled_at.

Raw schema

{
  "type": "object",
  "properties": {
    "output_type": {
      "description": "Studio type to render.",
      "type": "string"
    },
    "body": {
      "additionalProperties": true,
      "description": "Card fields for that type.",
      "type": "object"
    },
    "scheduled_at": {
      "description": "ISO-8601 time to post.",
      "type": "string"
    },
    "platforms": {
      "anyOf": [
        {
          "items": {
            "type": "string"
          },
          "type": "array"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "x, instagram, tiktok, linkedin, youtube, or everything."
    },
    "caption": {
      "anyOf": [
        {
          "type": "string"
        },
        {
          "type": "null"
        }
      ],
      "default": null,
      "description": "Caption for the scheduled post."
    },
    "timezone": {
      "default": "UTC",
      "description": "IANA timezone for scheduled_at.",
      "type": "string"
    }
  },
  "required": [
    "output_type",
    "body",
    "scheduled_at"
  ],
  "additionalProperties": false
}

README.md3 KBView on GitHub

Siren

Siren MCP

Your agent makes the images, captions, and videos for your brand, then posts them to your socials. You show Siren the brand once. After that you type post this in Cursor, Claude, ChatGPT, Codex, or Grok and it goes out.

Remote MCP server, Streamable HTTP, OAuth 2.1. No API keys to copy.


Server	`https://mcp.mysiren.ai/mcp`
Registry	`ai.mysiren/siren`
Docs	https://mysiren.ai/docs/mcp
Plans	One video is $9.99 once; plans start at $19 a month. MCP and videos are on every plan; credits are the only meter.

Connect

Claude Code

code

claude mcp add --transport http siren https://mcp.mysiren.ai/mcp

Claude (claude.ai): Settings → Connectors → Custom → https://mcp.mysiren.ai/mcp

Cursor: Settings → Tools & MCP → add a remote server, or in ~/.cursor/mcp.json:

json

{ "mcpServers": { "siren": { "url": "https://mcp.mysiren.ai/mcp" } } }

ChatGPT: Developer Mode on → Settings → Apps & Connectors → Create → https://mcp.mysiren.ai/mcp

Grok: grok.com/connectors → Custom, or grok mcp add --transport http siren https://mcp.mysiren.ai/mcp

The agent opens a consent page on app.mysiren.ai. Approve once. Posting stays off until you turn on Allow posting on that screen. Revoke any time under Developers.

Tools

Tool	What it does
`get_account`	Workspace, plan, credits, connected channels
`clarify_brief`	Turns a one-line ask into a brief Siren can render
`create_campaign`	Generates the asset. Optional `scheduled_at`, `timezone`, `platforms`
`render_asset`	Renders a specific output type
`list_runs`, `get_run`	Status and result URLs
`post_run`	Publishes a finished run to your connected channels now
`schedule_post`	Queues a finished run for a time in your timezone
`get_brand_dna`, `update_brand_dna`	Read and patch the brand profile
`list_product_screens`, `upload_product_screen`, `update_product_screen`, `delete_product_screen`	Product screenshots Siren can paint into assets
`studio_templates`	The 33 Studio data-card types, families, and body fields
`studio_card`	Render a Studio card. Optional live post
`studio_automate`	Create a Studio profile; returns generate curl and hook URLs
`studio_schedule`	Render a Studio card and queue a scheduled post

Posts go through the channels already connected in the Siren dashboard: X, LinkedIn, TikTok and YouTube (Instagram once Meta approves the app). The agent never sees your platform tokens.

Example

code

> Post an update about the new export feature. Use the dashboard screenshot.

The agent calls clarify_brief, then create_campaign, waits on get_run, and calls post_run. One image or film, a caption, and the post, on brand every time.

This repo

Listing and connect docs. The server is hosted at mcp.mysiren.ai. Questions: open an issue or write to hello@mysiren.ai.

Siren · a thousand voices, one signature.

Install

Tools (21)

get_accountlist_runsget_runcreate_campaignlist_filmsdescribe_filmclarify_briefrender_asset

Remote endpoint

Streamable HTTP

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

url

https://mcp.mysiren.ai/mcp

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "siren": {
      "command": "npx",
      "args": [
        "-y",
        "mcp-remote",
        "https://mcp.mysiren.ai/mcp"
      ]
    }
  }
}

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

MCP Server: ai.mysiren/siren

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

get_account

list_runs

get_run

create_campaign

list_films

describe_film

clarify_brief

render_asset

upload_media

post_run

schedule_post

get_brand_dna

update_brand_dna

list_product_screens

upload_product_screen

update_product_screen

delete_product_screen

studio_templates

studio_card

studio_automate

studio_schedule

Siren MCP

Connect

Tools

Example

This repo

Install

Remote endpoint

Related servers