SlideForge

Official7 toolsLive

by smartdatabrokers · Python

Deterministic, fully editable PowerPoint from typed slide intents. 200+ layouts, brand templates.

SlideForge MCP — PowerPoint slides for AI agents

SlideForge MCP (dev.slideforge/slideforge) is a remote MCP server that compiles typed slide intents into native, fully editable PowerPoint files (.pptx). It provides deterministic output with a fidelity manifest describing what was bound verbatim, and targets AI agents needing slide generation without local setup.

🛠️ Key Features

Deterministic, fully editable PowerPoint from typed slide intents
200+ layouts and brand templates
Fidelity manifest for verbatim bindings
Remote MCP server plus REST API
OAuth 2.1 for Claude Desktop & ChatG

🚀 Use Cases

Generate presentations for AI agents from structured slide intents
Produce editable .pptx output for downstream editing and review

⚡ Developer Benefits

No local install or Python environment required
Avoids python-pptx boilerplate
Deterministic compilation with explicit binding fidelity

⚠️ Limitations

Output fidelity is based on what is “bound verbatim” as stated in the fidelity manifest

Topics

agent-skillsai-agentsclaudeclaude-codemcpmcp-serverpowerpointpptxpresentations

Captured live from the server via tools/list.

browse_catalog

Browse the PowerPoint slide catalog progressively. No args -> form overview (when-to-use, bound fields, variant counts). family=<form> -> variant one-liners. q=<text> -> ranked search. variant=/prior_id= -> example payload. type=schema + family -> a compact family-level variant chooser (not a sendable contract); type=schema + family + variant -> that variant's exact payload contract (JSON Schema, capacity, field mapping, examples). Free. Code path: type=widgets = the add_widget() catalog (name=<widget> for its contract + thumbnail); type=helpers = python-pptx helper signatures. type=themes + an uploaded theme_id -> that template's branded FURNITURE layouts (its own cover/agenda/divider/closing slides + fill schemas + previews) — render via create_slide(form=template_layout, theme_id, data={layout, fills}).

Parameters11

family	string	optional
variant	string	optional
prior_id	string	optional
q	string	optional	Semantic search across all variants; returns ranked form/variant matches with scores.
limit	integer	optional	Max results (with q= or family=).
offset	integer	optional	Pagination offset (with q= or family=).
type	string	optional	Omit for the form overview (or family=/q= to drill in). schema (+family, optionally +variant=) = schema-first discovery: family only returns a compact variant chooser; family+variant returns that variant's exact machine-readable payload contract (JSON Schema for data, capacity limits, intent-field mapping, examples). widgets = the add_widget() catalog for mode=code (name=<widget> for its contract). helpers = python-pptx helper signatures. themes = list themes (built-in + your saved); Default appears first and can be omitted, or use any returned id as theme_id. brands = your brand kits with versions (theme_id=<slug> renders the default version, <slug>@<n> pins n).
name	string	optional	Widget name (with type=widgets): returns the full contract + worked example + a rendered thumbnail.
source	string	optional	Theme source filter (with type=themes). Default all (built-in + your saved).
top	integer	optional	Max results (with type=themes).
theme_id	string	optional	With type=themes: an uploaded theme's id -> its branded furniture layouts + fill schemas (render via create_slide(form=template_layout)).

Raw schema

{
  "type": "object",
  "properties": {
    "family": {
      "type": "string"
    },
    "variant": {
      "type": "string"
    },
    "prior_id": {
      "type": "string"
    },
    "q": {
      "type": "string",
      "description": "Semantic search across all variants; returns ranked form/variant matches with scores."
    },
    "limit": {
      "type": "integer",
      "description": "Max results (with q= or family=)."
    },
    "offset": {
      "type": "integer",
      "description": "Pagination offset (with q= or family=)."
    },
    "type": {
      "type": "string",
      "description": "Omit for the form overview (or family=/q= to drill in). schema (+family, optionally +variant=) = schema-first discovery: family only returns a compact variant chooser; family+variant returns that variant's exact machine-readable payload contract (JSON Schema for data, capacity limits, intent-field mapping, examples). widgets = the add_widget() catalog for mode=code (name=<widget> for its contract). helpers = python-pptx helper signatures. themes = list themes (built-in + your saved); Default appears first and can be omitted, or use any returned id as theme_id. brands = your brand kits with versions (theme_id=<slug> renders the default version, <slug>@<n> pins n)."
    },
    "name": {
      "type": "string",
      "description": "Widget name (with type=widgets): returns the full contract + worked example + a rendered thumbnail."
    },
    "source": {
      "type": "string",
      "enum": [
        "all",
        "default",
        "custom",
        "saved",
        "uploaded"
      ],
      "description": "Theme source filter (with type=themes). Default all (built-in + your saved)."
    },
    "top": {
      "type": "integer",
      "description": "Max results (with type=themes)."
    },
    "theme_id": {
      "type": "string",
      "description": "With type=themes: an uploaded theme's id -> its branded furniture layouts + fill schemas (render via create_slide(form=template_layout))."
    }
  }
}

plan_slide

Plan a PowerPoint slide before rendering (free): send a short brief, get ranked candidates + a separated verdict — route (which slide: selected|needs_confirmation|ambiguous), input (can it render: ready|extractable_from_brief|needs_structured_data) and next_action. Free (one embedding). Then call create_slide with the chosen form(+variant). route.confidence: calibrated = measured P(route correct) with label high/medium/low cut on it; retrieval_score/retrieval_margin = the raw family-aggregated classifier values (not probabilities; margin can be negative when families contest); source = classifier | structural_router (LLM-rescued). candidate_margin on the top candidate = literal gap between the two shown scores.

Parameters4

brief	string	required
top	integer	optional
escalate	boolean	optional	Default true: on a low-confidence route the plan runs the SAME LLM rescue create_slide would (small COGS on that tail only), so plan and create always agree. Set false for a classifier-only, fully free plan (response then flags will_escalate + create_slide_behavior).
variant_policy	string	optional	production_safe: if the top routed variant is draft/beta, the family's demo-safe sibling leads and route reports both best_semantic and best_production_safe.

Raw schema

{
  "type": "object",
  "properties": {
    "brief": {
      "type": "string"
    },
    "top": {
      "type": "integer"
    },
    "escalate": {
      "type": "boolean",
      "description": "Default true: on a low-confidence route the plan runs the SAME LLM rescue create_slide would (small COGS on that tail only), so plan and create always agree. Set false for a classifier-only, fully free plan (response then flags will_escalate + create_slide_behavior)."
    },
    "variant_policy": {
      "type": "string",
      "enum": [
        "best_semantic_match",
        "production_safe"
      ],
      "description": "production_safe: if the top routed variant is draft/beta, the family's demo-safe sibling leads and route reports both best_semantic and best_production_safe."
    }
  },
  "required": [
    "brief"
  ]
}

create_slide

Create one PowerPoint slide (.pptx, native, editable) from a structured intent in ONE call: pick a `form` from the menu and put your content in the typed fields (placed on the slide as given), or pass a `brief` and let the server route it. Fields tagged (per-form) bind only where the form has that slot — ignored-with-warning elsewhere; see each form's `binds` in browse_catalog. BLOCKED ($0)? If an error has `can_autofix:true`, merge its `patch` into the args at `patch_target`. Unchanged retries repeat the block. New form: browse_catalog(type=schema) first. FORM MENU: agenda_list: an ordered list of sections/topics or learning objectives to walk through bar_rank_chart: bars comparing magnitudes across categories calendar_grid: events on a real calendar - week planner (day x hour) or month grid with event chips (data.events) card_grid: several equal, unordered peer blocks (features, options, pillars, a concept's defined parts, rules/guidelines/common mistakes) case_story: one named story told as evidence: challenge, action, measured result comparison_matrix: options x criteria grid: data.columns x data.rows cycle_flow: a closed loop of ordered stages where the last feeds the first (recurring process) data_table: a plain factual table of records by fields editorial_split: two side-by-side halves: contrast (before/after, problem/solution) or copy/numbered steps beside a picture (image_src) exercise_prompt: an exercise/practice/discussion prompt: instruction + hints; optional problem items with blank answer boxes funnel: a quantity narrowing through ordered stages gantt_plan: tasks as bars across named periods on a schedule grid gauge_score: one score on a dial against a scale hero_statement: a statement slide: covers (title/image-led/exec), from->to/thesis-quote transitions, statement/contact/next-steps closings; supporting points -> takeaway_stack, contacts -> data.contacts, next steps -> data.next_steps hub_spoke: one central element with several elements connected around it image_story: a picture shown WHOLE (uncropped) + prose and up to 4 labelled blocks beside it, or a 1-6 picture/placeholder gallery (data.images) kpi_metrics: a metrics dashboard: headline metric cards; data.sections (Highlights/Risks/Asks) makes it an exec summary / QBR snapshot layer_stack: stacked layers where higher sits on, and depends on, lower linear_flow: ordered process stages read left to right (or inputs to process to outputs) maturity_staircase: ascending levels climbing to a higher state nested_magnitude: nested containment - each level contains the next org_structure: a reporting hierarchy / org tree position_map: items placed by two axes - named 2x2 cells or scatter positions pyramid_hierarchy: a triangle of stacked tiers, foundation to apex ramp_curve: a continuous rising wedge split into phases - effort or value accumulating over time section_divider: a section-break: big section number + title; blocks = agenda progress chips (emphasis=primary = current) segment_wheel: a wheel of equal segments around a center - peer categories in the round (composition, not flow) status_dashboard: initiatives/workstreams tracked by status, owner, progress strategic_fork: one origin splitting into two mutually exclusive paths, one recommended swimlane_flow: actor/function lanes by phases, task cells, handoffs across lanes swot: the four-quadrant strengths / weaknesses / opportunities / threats grid system_flow_map: architecture/system components: panels with internals (edges optional) or nodes wired by directed arrows takeaway_stack: a title plus a few supporting points, each with one line of detail (executive summary, key findings); optional closing ask timeline_roadmap: milestones/phases laid out along a time axis trend_chart: one or more series plotted over time value_chain: support bands over primary activity columns flowing into a goal arrowhead (data.support = the bands) visual_showcase: one dominant screenshot/image with numbered callouts pointing into it waterfall_bri

Parameters42

form	string	optional	the form menu pick (see description) — the routing field
form_description	string	optional
headline	string	optional	the assertion-style slide title
context	string	optional	one-line subtitle/standfirst
subject	string	optional	central entity for forms that have one — hub label, org root, section #, fork origin, media label (per-form).
blocks	array	optional	list: [{"label","sub","detail":[str],"emphasis","icon":lucide-name,"metric":{value,label}}]
metric	object	optional
data	object	optional	family-specific payload — see the documented shapes
takeaway	string	optional	optional verdict band (per-form). Put the so-what in the headline; add only for a verdict the title can't carry — not every slide.
caution	string	optional	one-line risk / caveat callout (per-form).
highlight	string	optional	one-line emphasis callout (per-form).
source_note	string	optional	source / footnote line (per-form).
date	string	optional	date callout (per-form).
image_src	string	optional	https URL \| asset:<id> for image-bearing forms
image_prompt	string	optional	generate an image when no image_src (+$0.05)
brief	string	optional	prose fallback / extra context for fills
theme_id	string	optional	Optional theme id from browse_catalog(type=themes). Omit for Default (slideforge_standard).
name	string	optional
variant	string	optional	pin a specific variant within the form (list them via browse_catalog). Unknown variant -> rejected ($0) with the valid list; set allow_variant_fallback to render the family default instead.
allow_variant_fallback	boolean	optional	If the pinned variant is unknown, render the form's default variant (with a warning) instead of rejecting. Default false.
variant_policy	string	optional	Routed-variant maturity policy: production_safe = if the ROUTED variant is draft/beta, render the family's demo-safe sibling instead (warning names both). Never overrides an explicit variant=. Default best_semantic_match.
allow_low_confidence	boolean	optional	Brief routing only: by default a brief that doesn't match a form clearly returns status=needs_confirmation + candidates at cost:0 (no guessed render). Set true to render the top guess and bill it. Default false.
allow_fabrication	boolean	optional	Brief mode only: a bare brief on a DATA form (kpi/funnel/comparison/…) returns would_fabricate at $0 rather than INVENT numbers. Send typed fields for verbatim, or true to let the brief author them (fidelity=ai_completed). Default false.
allow_truncation	boolean	optional	More items than the form holds blocks (it would drop your data); the response names the dropped count + a suggested_split. true renders the capacity subset (fidelity=verbatim_truncated). Default false.
dry_run	boolean	optional	Free pre-commit check (intent or mode=code), cost:0, no PPTX: status + warnings/errors, plus fidelity_forecast (verbatim\|mixed\|ai_completed\|would_reject) and which fields bind vs get authored. Fix errors, re-call with dry_run=false to render.
quality_profile	string	optional	Thresholds layout.presentation_ready is judged against (executive strictest). Measurement only — never blocks a render or changes cost.
min_font_pt	number	optional	Binding type floor for prose (exhibit furniture has its own). Type grows to meet it; content that can't fit is a $0 min_font_not_met naming the size needed. Typical: 12.
direction	string	optional	rtl typesets AND mirrors the slide right-to-left (Arabic/Hebrew). Never inferred — pass it.
imagery	string	optional	Cover/section-divider imagery: photo (default — curated stock photo, half-bleed), wash (abstract color wash), off (plain panel, no photo — only when asked). Content slides are never photo-decorated.
imagery_tag	string	optional	Subject/industry: steers cover/section photos AND the topical palette. Omit = general; `education` = teaching.
styling	string	optional	Topical design on default themes (default on; the note names it): designed cover + a subject palette (from imagery_tag, or the brief). clean = neutral. Pins never take it.
force_render	boolean	optional	On completed_with_errors, pptx_url is null (broken slide). Set true to get it anyway. No cost/status effect.
code	string	optional	Python code defining build(prs). Canvas 13.33×7.5", coords in inches. Pre-imported: Presentation, Inches, Pt, Emu, RGBColor, MSO_ANCHOR, PP_ALIGN. Helpers: add_text_box(slide, left, top, w, h, text, font_size=12, bold=False, color=None), add_box(slide, left, top, w, h, fill_color=None, line_color=None, corner_radius=0.05), add_icon, add_image (src = path or https://); theme_color(name) → RGBColor. add_widget(slide, name, x, y, w, h, params=\|content=, theme=THEME) draws board-grade SSG widgets/charts (cards, waterfall, gantt, funnel…) — names via `browse_catalog(type=widgets)`. Use font_size=, not size=; use fill_color=, not fill=. When chrome is supplied, use `build(prs, slide)` — chrome is pre-rendered. Helper signatures: `browse_catalog(type=helpers)`.
job_id	string	optional	Previous job ID (for mode=status, or mode=code patching)
replacements	array	optional	String replacements on loaded code [{old, new}] (for mode=code with job_id)
language	string	optional	Target language (default: en)
include_preview	string	optional	Inline-preview PAYLOAD only (not execution). Default: default (768px). none omits the inline image and returns just the URLs — it does NOT change sync/async. Use `wait` to control execution.
detail	string	optional	Response verbosity. Default `compact`: status, form/variant, fidelity (verbatim\|mixed\|ai_completed), warnings[]/errors[] (only when present), urls, cost. `full` adds a debug object (engine internals, verify events, latency buckets).
verify	string	optional	mode=code tier. Default `lint`: static geometry linter (overlap/off-canvas/zero-size) + composer content validators — no LLM. `lint+vlm` adds a VLM second-look (~+3s) and makes a blank/contentless render a $0 error, not a billed warning. `off` skips checks.
wait	string	optional	AI-image slides block ~10-15s; `false` returns a job_id to poll, not block (mode=brief).
logo_id	string	optional	Optional brand logo (from upload_asset purpose=logo) drawn as chrome on content slides; covers/section breaks stay clean.
mode	string	optional	Default: structured intent / brief. safe = validate-then-render in ONE call (renders + bills only if faithful; else $0 invalid report with the fix — recommended, no dry_run round-trip). code = python-pptx escape. status = poll.

Raw schema

{
  "type": "object",
  "properties": {
    "form": {
      "type": "string",
      "description": "the form menu pick (see description) — the routing field"
    },
    "form_description": {
      "type": "string"
    },
    "headline": {
      "type": "string",
      "description": "the assertion-style slide title"
    },
    "context": {
      "type": "string",
      "description": "one-line subtitle/standfirst"
    },
    "subject": {
      "type": "string",
      "description": "central entity for forms that have one — hub label, org root, section #, fork origin, media label (per-form)."
    },
    "blocks": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "list: [{\"label\",\"sub\",\"detail\":[str],\"emphasis\",\"icon\":lucide-name,\"metric\":{value,label}}]"
    },
    "metric": {
      "type": "object"
    },
    "data": {
      "type": "object",
      "description": "family-specific payload — see the documented shapes"
    },
    "takeaway": {
      "type": "string",
      "description": "optional verdict band (per-form). Put the so-what in the headline; add only for a verdict the title can't carry — not every slide."
    },
    "caution": {
      "type": "string",
      "description": "one-line risk / caveat callout (per-form)."
    },
    "highlight": {
      "type": "string",
      "description": "one-line emphasis callout (per-form)."
    },
    "source_note": {
      "type": "string",
      "description": "source / footnote line (per-form)."
    },
    "date": {
      "type": "string",
      "description": "date callout (per-form)."
    },
    "image_src": {
      "type": "string",
      "description": "https URL | asset:<id> for image-bearing forms"
    },
    "image_prompt": {
      "type": "string",
      "description": "generate an image when no image_src (+$0.05)"
    },
    "brief": {
      "type": "string",
      "description": "prose fallback / extra context for fills"
    },
    "theme_id": {
      "type": "string",
      "description": "Optional theme id from browse_catalog(type=themes). Omit for Default (slideforge_standard)."
    },
    "name": {
      "type": "string"
    },
    "variant": {
      "type": "string",
      "description": "pin a specific variant within the form (list them via browse_catalog). Unknown variant -> rejected ($0) with the valid list; set allow_variant_fallback to render the family default instead."
    },
    "allow_variant_fallback": {
      "type": "boolean",
      "description": "If the pinned variant is unknown, render the form's default variant (with a warning) instead of rejecting. Default false."
    },
    "variant_policy": {
      "type": "string",
      "enum": [
        "best_semantic_match",
        "production_safe"
      ],
      "description": "Routed-variant maturity policy: production_safe = if the ROUTED variant is draft/beta, render the family's demo-safe sibling instead (warning names both). Never overrides an explicit variant=. Default best_semantic_match."
    },
    "allow_low_confidence": {
      "type": "boolean",
      "description": "Brief routing only: by default a brief that doesn't match a form clearly returns status=needs_confirmation + candidates at cost:0 (no guessed render). Set true to render the top guess and bill it. Default false."
    },
    "allow_fabrication": {
      "type": "boolean",
      "description": "Brief mode only: a bare brief on a DATA form (kpi/funnel/comparison/…) returns would_fabricate at $0 rather than INVENT numbers. Send typed fields for verbatim, or true to let the brief author them (fidelity=ai_completed). Default false."
    },
    "allow_truncation": {
      "type": "boolean",
      "description": "More items than the form holds blocks (it would drop your data); the response names the dropped count + a suggested_split. true renders the capacity subset (fidelity=verbatim_truncated). Default false."
    },
    "dry_run": {
      "type": "boolean",
      "description": "Free pre-commit check (intent or mode=code), cost:0, no PPTX: status + warnings/errors, plus fidelity_forecast (verbatim|mixed|ai_completed|would_reject) and which fields bind vs get authored. Fix errors, re-call with dry_run=false to render."
    },
    "quality_profile": {
      "type": "string",
      "enum": [
        "executive",
        "technical",
        "appendix"
      ],
      "description": "Thresholds layout.presentation_ready is judged against (executive strictest). Measurement only — never blocks a render or changes cost."
    },
    "min_font_pt": {
      "type": "number",
      "minimum": 6,
      "maximum": 40,
      "description": "Binding type floor for prose (exhibit furniture has its own). Type grows to meet it; content that can't fit is a $0 min_font_not_met naming the size needed. Typical: 12."
    },
    "direction": {
      "type": "string",
      "enum": [
        "ltr",
        "rtl"
      ],
      "description": "rtl typesets AND mirrors the slide right-to-left (Arabic/Hebrew). Never inferred — pass it."
    },
    "imagery": {
      "type": "string",
      "enum": [
        "photo",
        "wash",
        "off"
      ],
      "description": "Cover/section-divider imagery: photo (default — curated stock photo, half-bleed), wash (abstract color wash), off (plain panel, no photo — only when asked). Content slides are never photo-decorated."
    },
    "imagery_tag": {
      "type": "string",
      "enum": [
        "general",
        "agriculture",
        "construction",
        "education",
        "energy",
        "finance",
        "government",
        "healthcare",
        "logistics",
        "manufacturing",
        "retail",
        "technology",
        "travel"
      ],
      "description": "Subject/industry: steers cover/section photos AND the topical palette. Omit = general; `education` = teaching."
    },
    "styling": {
      "type": "string",
      "enum": [
        "topical",
        "clean"
      ],
      "description": "Topical design on default themes (default on; the note names it): designed cover + a subject palette (from imagery_tag, or the brief). clean = neutral. Pins never take it."
    },
    "force_render": {
      "type": "boolean",
      "description": "On completed_with_errors, pptx_url is null (broken slide). Set true to get it anyway. No cost/status effect."
    },
    "code": {
      "type": "string",
      "description": "Python code defining build(prs). Canvas 13.33×7.5\", coords in inches. Pre-imported: Presentation, Inches, Pt, Emu, RGBColor, MSO_ANCHOR, PP_ALIGN. Helpers: add_text_box(slide, left, top, w, h, text, font_size=12, bold=False, color=None), add_box(slide, left, top, w, h, fill_color=None, line_color=None, corner_radius=0.05), add_icon, add_image (src = path or https://); theme_color(name) → RGBColor. add_widget(slide, name, x, y, w, h, params=|content=, theme=THEME) draws board-grade SSG widgets/charts (cards, waterfall, gantt, funnel…) — names via `browse_catalog(type=widgets)`. Use font_size=, not size=; use fill_color=, not fill=. When chrome is supplied, use `build(prs, slide)` — chrome is pre-rendered. Helper signatures: `browse_catalog(type=helpers)`."
    },
    "job_id": {
      "type": "string",
      "description": "Previous job ID (for mode=status, or mode=code patching)"
    },
    "replacements": {
      "type": "array",
      "description": "String replacements on loaded code [{old, new}] (for mode=code with job_id)",
      "items": {
        "type": "object",
        "properties": {
          "old": {
            "type": "string",
            "description": "Exact string to find"
          },
          "new": {
            "type": "string",
            "description": "Replacement string"
          }
        },
        "required": [
          "old",
          "new"
        ]
      }
    },
    "language": {
      "type": "string",
      "enum": [
        "en",
        "de",
        "fr",
        "es",
        "it",
        "pt",
        "nl",
        "pl",
        "ru",
        "uk"
      ],
      "description": "Target language (default: en)"
    },
    "include_preview": {
      "type": "string",
      "enum": [
        "none",
        "small",
        "default",
        "full"
      ],
      "description": "Inline-preview PAYLOAD only (not execution). Default: default (768px). none omits the inline image and returns just the URLs — it does NOT change sync/async. Use `wait` to control execution."
    },
    "detail": {
      "type": "string",
      "enum": [
        "compact",
        "full"
      ],
      "description": "Response verbosity. Default `compact`: status, form/variant, fidelity (verbatim|mixed|ai_completed), warnings[]/errors[] (only when present), urls, cost. `full` adds a debug object (engine internals, verify events, latency buckets)."
    },
    "verify": {
      "type": "string",
      "enum": [
        "off",
        "lint",
        "lint+vlm",
        "full"
      ],
      "description": "mode=code tier. Default `lint`: static geometry linter (overlap/off-canvas/zero-size) + composer content validators — no LLM. `lint+vlm` adds a VLM second-look (~+3s) and makes a blank/contentless render a $0 error, not a billed warning. `off` skips checks."
    },
    "wait": {
      "type": "string",
      "enum": [
        "auto",
        "true",
        "false"
      ],
      "description": "AI-image slides block ~10-15s; `false` returns a job_id to poll, not block (mode=brief)."
    },
    "logo_id": {
      "type": "string",
      "description": "Optional brand logo (from upload_asset purpose=logo) drawn as chrome on content slides; covers/section breaks stay clean."
    },
    "mode": {
      "type": "string",
      "enum": [
        "safe",
        "brief",
        "code",
        "status"
      ],
      "description": "Default: structured intent / brief. safe = validate-then-render in ONE call (renders + bills only if faithful; else $0 invalid report with the fix — recommended, no dry_run round-trip). code = python-pptx escape. status = poll."
    }
  }
}

create_deck

Create a complete PowerPoint presentation (.pptx): a whole multi-slide deck, native and editable, in one call. `slides` is a list of create_slide intents (same form menu + data shapes — see create_slide). Slides fill in parallel and merge into one themed PPTX with page numbers. Include furniture: a hero_statement cover, section_divider breaks, and a closing (hero_statement variant=contact_closing via blocks-free slots). BLOCKED ($0)? If an error has `can_autofix:true`, merge its `patch` into the args at `patch_target`. Unchanged retries repeat the block. New form: browse_catalog(type=schema) first. Also: mode=assemble merges existing slide job_ids as-rendered (free; theme_id does NOT re-theme them — render with create_deck(slides=[…], theme_id=…) for a unified theme); mode=fork clones a deck (free). Polling: deck_id == job_id — manage_account(action=job, job_id=<deck_id>).

Parameters17

slides	array	optional	each item is a create_slide intent (same form menu, typed fields, and data shapes as create_slide).
theme_id	string	optional
name	string	optional
styling	string	optional	Deck-level topical-design switch, inherited by every slide (a slide-level styling wins). See create_slide.styling.
imagery	string	optional	Deck-level imagery mode, inherited by every slide (a slide-level imagery wins). See create_slide.imagery.
imagery_tag	string	optional	Deck-level subject declaration, inherited by every slide (a slide-level imagery_tag wins). Declare it once for a whole deck. See create_slide.imagery_tag.
direction	string	optional	Deck-level writing direction, inherited by every slide (a slide-level direction wins) — set it once for an Arabic/Hebrew deck. Covers/dividers rendered on an UPLOADED brand template keep that template's own layout direction. See create_slide.direction.
force_render	boolean	optional	IGNORED (deck-level). pptx_url is always returned when at least one slide rendered, so there is nothing to force. Still meaningful on create_slide.
allow_partial	boolean	optional	IGNORED. A deck bills per rendered slide and always returns its pptx; slides that failed or rendered badly are free and named in repair_actions.
strict_policy	object	optional	Optional CI-style gate for automated report pipelines. dry_run returns policy_result; render returns rejected/cost:0 if the policy fails.
job_ids	array	optional	Slide job IDs to merge (for mode=assemble)
deck_id	string	optional	Existing deck ID (for mode=fork, or mode=render to update)
title	string	optional	Deck title (PowerPoint metadata)
language	string	optional	Target language
mode	string	optional	Default render. assemble/fork are free deck plumbing.
dry_run	boolean	optional	Deck-level free pre-flight (cost:0, NO render/PPTX): returns a per-slide validation manifest [{i, form, fidelity_forecast, status, errors}] so you can fix bad slides before spending. A deck is one artifact, so validation is all-or-nothing — put dry_run here, not on individual slides. Resend without dry_run to render.
logo_id	string	optional	Optional brand logo (from upload_asset purpose=logo) applied as chrome to every content slide in the deck.

Raw schema

{
  "type": "object",
  "properties": {
    "slides": {
      "type": "array",
      "items": {
        "type": "object"
      },
      "description": "each item is a create_slide intent (same form menu, typed fields, and data shapes as create_slide)."
    },
    "theme_id": {
      "type": "string"
    },
    "name": {
      "type": "string"
    },
    "styling": {
      "type": "string",
      "enum": [
        "topical",
        "clean"
      ],
      "description": "Deck-level topical-design switch, inherited by every slide (a slide-level styling wins). See create_slide.styling."
    },
    "imagery": {
      "type": "string",
      "enum": [
        "photo",
        "wash",
        "off"
      ],
      "description": "Deck-level imagery mode, inherited by every slide (a slide-level imagery wins). See create_slide.imagery."
    },
    "imagery_tag": {
      "type": "string",
      "enum": [
        "general",
        "agriculture",
        "construction",
        "education",
        "energy",
        "finance",
        "government",
        "healthcare",
        "logistics",
        "manufacturing",
        "retail",
        "technology",
        "travel"
      ],
      "description": "Deck-level subject declaration, inherited by every slide (a slide-level imagery_tag wins). Declare it once for a whole deck. See create_slide.imagery_tag."
    },
    "direction": {
      "type": "string",
      "enum": [
        "ltr",
        "rtl"
      ],
      "description": "Deck-level writing direction, inherited by every slide (a slide-level direction wins) — set it once for an Arabic/Hebrew deck. Covers/dividers rendered on an UPLOADED brand template keep that template's own layout direction. See create_slide.direction."
    },
    "force_render": {
      "type": "boolean",
      "description": "IGNORED (deck-level). pptx_url is always returned when at least one slide rendered, so there is nothing to force. Still meaningful on create_slide."
    },
    "allow_partial": {
      "type": "boolean",
      "description": "IGNORED. A deck bills per rendered slide and always returns its pptx; slides that failed or rendered badly are free and named in repair_actions."
    },
    "strict_policy": {
      "type": "object",
      "properties": {
        "reject_ai_completed": {
          "type": "boolean",
          "description": "Reject slides whose content was fully AI-completed."
        },
        "reject_mixed": {
          "type": "boolean",
          "description": "Reject slides with mixed verbatim and AI-completed content."
        },
        "reject_truncated": {
          "type": "boolean",
          "description": "Reject slides with truncated supplied content."
        },
        "reject_ignored_fields": {
          "type": "boolean",
          "description": "Reject slides whose supplied fields were not rendered (fidelity=partial / field_ignored)."
        },
        "reject_field_warnings": {
          "type": "boolean",
          "description": "Reject slides carrying any field-binding warning (field_ignored, input_shape_hint, normalized, variant_fallback)."
        },
        "reject_draft_variants": {
          "type": "boolean",
          "description": "Reject slides rendered by a draft-maturity variant (see each slide's variant_maturity warning)."
        },
        "min_font_pt": {
          "type": "number",
          "description": "Reject slides whose reported minimum font size is below this point size."
        },
        "max_density": {
          "type": "string",
          "enum": [
            "good",
            "medium",
            "high"
          ],
          "description": "Reject slides whose quality.density is above this level."
        }
      },
      "description": "Optional CI-style gate for automated report pipelines. dry_run returns policy_result; render returns rejected/cost:0 if the policy fails."
    },
    "job_ids": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Slide job IDs to merge (for mode=assemble)"
    },
    "deck_id": {
      "type": "string",
      "description": "Existing deck ID (for mode=fork, or mode=render to update)"
    },
    "title": {
      "type": "string",
      "description": "Deck title (PowerPoint metadata)"
    },
    "language": {
      "type": "string",
      "enum": [
        "en",
        "de",
        "fr",
        "es",
        "it",
        "pt",
        "nl",
        "pl",
        "ru",
        "uk"
      ],
      "description": "Target language"
    },
    "mode": {
      "type": "string",
      "enum": [
        "render",
        "assemble",
        "fork"
      ],
      "description": "Default render. assemble/fork are free deck plumbing."
    },
    "dry_run": {
      "type": "boolean",
      "description": "Deck-level free pre-flight (cost:0, NO render/PPTX): returns a per-slide validation manifest [{i, form, fidelity_forecast, status, errors}] so you can fix bad slides before spending. A deck is one artifact, so validation is all-or-nothing — put dry_run here, not on individual slides. Resend without dry_run to render."
    },
    "logo_id": {
      "type": "string",
      "description": "Optional brand logo (from upload_asset purpose=logo) applied as chrome to every content slide in the deck."
    }
  },
  "required": []
}

translate_deck

Translate a PowerPoint (.pptx) deck preserving all formatting. $0.02/slide. Supports 32 languages (Latin, Cyrillic, Greek scripts). Provide job_id (from a previous create_slide/create_deck), pptx_url, or pptx_base64.

Parameters10

target_language	string	required	Target language (required)
source_language	string	optional	Source language or 'auto' (default auto)
job_id	string	optional	Source: previous slide/deck job ID (preferred — no file transfer needed)
pptx_url	string	optional	Source: HTTPS URL to .pptx
pptx_base64	string	optional	Source: Base64-encoded .pptx (max ~10 MB)
include_notes	boolean	optional	Translate speaker notes (default false)
include_tables	boolean	optional	Translate table cells (default true)
concise_mode	boolean	optional	Prefer shorter translations for tight text boxes
name	string	optional	Job name
include_preview	string	optional	Wait+embed preview (default=wait)

Raw schema

{
  "type": "object",
  "properties": {
    "target_language": {
      "type": "string",
      "enum": [
        "en",
        "de",
        "fr",
        "es",
        "it",
        "pt",
        "nl",
        "sv",
        "da",
        "no",
        "fi",
        "is",
        "pl",
        "cs",
        "sk",
        "hu",
        "ro",
        "hr",
        "sl",
        "et",
        "lt",
        "lv",
        "ru",
        "uk",
        "bg",
        "sr",
        "tr",
        "ca",
        "gl",
        "id",
        "vi",
        "el"
      ],
      "description": "Target language (required)"
    },
    "source_language": {
      "type": "string",
      "description": "Source language or 'auto' (default auto)"
    },
    "job_id": {
      "type": "string",
      "description": "Source: previous slide/deck job ID (preferred — no file transfer needed)"
    },
    "pptx_url": {
      "type": "string",
      "description": "Source: HTTPS URL to .pptx"
    },
    "pptx_base64": {
      "type": "string",
      "description": "Source: Base64-encoded .pptx (max ~10 MB)"
    },
    "include_notes": {
      "type": "boolean",
      "description": "Translate speaker notes (default false)"
    },
    "include_tables": {
      "type": "boolean",
      "description": "Translate table cells (default true)"
    },
    "concise_mode": {
      "type": "boolean",
      "description": "Prefer shorter translations for tight text boxes"
    },
    "name": {
      "type": "string",
      "description": "Job name"
    },
    "include_preview": {
      "type": "string",
      "enum": [
        "none",
        "small",
        "default"
      ],
      "description": "Wait+embed preview (default=wait)"
    }
  },
  "required": [
    "target_language"
  ]
}

upload_asset

Upload assets for PowerPoint (.pptx) generation: company template, logo, image, or document — or AI-generate an image. Purposes: • logo — company logo for chrome (PNG/JPG/SVG, max 5MB) → logo_id • image — image for the Image component (max 10MB) → asset_id • theme — company template PPTX → theme_id; slides with it render NATIVELY on the template (masters/layouts/chrome) • generate_image — AI-generate via `prompt` → asset_id ($0.05) • translate — PPTX to translate → deck job_id ($0.02/slide; requires `target_language`) • pdf — PDF → editable slides; pass `target_language` to also translate • recreate — image OF a slide → editable PPTX slide ($0.10; honest annotate/preserve fallback, refusals free). Use `image` to just place a picture Files >3MB (pdf/translate/theme) — and recreate on chat hosts — omit `data`: a drop-zone appears in the result card; bytes never pass through the agent.

Parameters10

purpose	string	required	Asset type (required). brand = a .pptx/.potx corporate template imported as your brand kit (theme is the same thing under its old name).
data	string	optional	Base64-encoded file content. Required for logo/image/theme/translate. Optional for pdf — omit to get a drop-zone (recommended for files >3MB).
filename	string	optional	Original filename (for type detection)
prompt	string	optional	Image description (required when purpose=generate_image)
size	string	optional	Image dimensions for generate_image (default 1024×1024)
quality	string	optional	draft = Flux Schnell. balanced (default) = Gemini Flash Image. premium = Imagen 4 Fast. Overridden by `model`.
model	string	optional	Explicit gateway model ID. Overrides `quality`.
position	string	optional	Logo position: top-left / top-right / bottom-left / bottom-right
theme_name	string	optional	Name for extracted theme (purpose=theme)
target_language	string	optional	Required for purpose=translate. Optional for purpose=pdf — chains pdf→pptx→translate in one call.

Raw schema

{
  "type": "object",
  "properties": {
    "purpose": {
      "type": "string",
      "enum": [
        "logo",
        "image",
        "theme",
        "brand",
        "generate_image",
        "translate",
        "pdf",
        "recreate"
      ],
      "description": "Asset type (required). brand = a .pptx/.potx corporate template imported as your brand kit (theme is the same thing under its old name)."
    },
    "data": {
      "type": "string",
      "description": "Base64-encoded file content. Required for logo/image/theme/translate. Optional for pdf — omit to get a drop-zone (recommended for files >3MB)."
    },
    "filename": {
      "type": "string",
      "description": "Original filename (for type detection)"
    },
    "prompt": {
      "type": "string",
      "description": "Image description (required when purpose=generate_image)"
    },
    "size": {
      "type": "string",
      "enum": [
        "1024x1024",
        "1792x1024",
        "1024x1792"
      ],
      "description": "Image dimensions for generate_image (default 1024×1024)"
    },
    "quality": {
      "type": "string",
      "enum": [
        "draft",
        "balanced",
        "premium"
      ],
      "description": "draft = Flux Schnell. balanced (default) = Gemini Flash Image. premium = Imagen 4 Fast. Overridden by `model`."
    },
    "model": {
      "type": "string",
      "description": "Explicit gateway model ID. Overrides `quality`."
    },
    "position": {
      "type": "string",
      "description": "Logo position: top-left / top-right / bottom-left / bottom-right"
    },
    "theme_name": {
      "type": "string",
      "description": "Name for extracted theme (purpose=theme)"
    },
    "target_language": {
      "type": "string",
      "enum": [
        "en",
        "de",
        "fr",
        "es",
        "it",
        "pt",
        "nl",
        "sv",
        "da",
        "no",
        "fi",
        "is",
        "pl",
        "cs",
        "sk",
        "hu",
        "ro",
        "hr",
        "sl",
        "et",
        "lt",
        "lv",
        "ru",
        "uk",
        "bg",
        "sr",
        "tr",
        "ca",
        "gl",
        "id",
        "vi",
        "el"
      ],
      "description": "Required for purpose=translate. Optional for purpose=pdf — chains pdf→pptx→translate in one call."
    }
  },
  "required": [
    "purpose"
  ]
}

manage_account

SlideForge account for PowerPoint generation: balance, billing, job history, feedback, data controls. All free. Actions: status (balance+plan), usage (spend breakdown), jobs (history), job (single job detail — slide jobs include `quality_warnings[]`; deck jobs add `slides_completed/slides_failed/failed_slides[]`), feedback (submit), feedback_list (read your reports back: status + resolution), onboarding (capabilities overview), topup (Stripe checkout link; wallet credits automatically), webhooks/webhook_add/webhook_remove/webhook_test (push endpoint instead of polling to terminal), download_url (fresh short-TTL PPTX link for an owned job — when a result carries no inline URL), security_status (retention + access-model + deletion posture), delete_job (irreversible: job + versions + files) Action delete_asset irreversibly deletes a user-owned uploaded/generated image asset.

Parameters17

action	string	required	Operation (required). feedback → report a defect or request against a render; pass job_id so it is actionable, and ask the user before filing. feedback_list → read YOUR OWN filed reports back, with `status` and the `resolution` written when one was acted on: check it before working around a defect you reported earlier, because it may already be fixed. brand_report → the per-token fidelity report for one of your brand kits (pass theme_id). topup → mints a Stripe checkout link the user pays at directly (wallet credits automatically) — use when a render is refused for balance. reports → list report types; webhook_add registers a push endpoint instead of polling — see the url/events props. delete_job is irreversible. delete_asset is irreversible for user-owned image assets.
job_id	string	optional	Job ID (for action=job, action=download_url and action=delete_job)
limit	integer	optional	Max rows (action=jobs default 10; action=feedback_list default 50, max 100)
status	string	optional	Filter — action=jobs: queued/generating/complete/failed; action=feedback_list: open/resolved
include_children	boolean	optional	For action=jobs: include deck child slides (each carries parent_deck_id) so a deck's slides are discoverable by listing. Default false (parents only). Deck rows roll child cost up to the deck.
message	string	optional	What went wrong or what you want, in the user's own words (for action=feedback).
category	string	optional	Feedback category (action=feedback to file under it, action=feedback_list to filter by it). The first nine are slide-quality categories — pair them with job_id.
severity	string	optional	For action=feedback: `bug` = it is broken, `quality` = it rendered but reads poorly, `suggestion` = a request. Defaults to suggestion, so file real defects explicitly or they are triaged as wishes.
days	integer	optional	Lookback period (for action=usage, default 30)
amount	number	optional	USD top-up amount (for action=topup, default 10, min 10, max 1000). Volume bonus: $50→+10%, $100→+15%, $200→+20%.
detail	boolean	optional	For action=status only: default false masks identity fields; true returns full email/user_id diagnostics for the authenticated user.
include_preview	string	optional	Preview (for action=job)
slug	string	optional	Report slug (for action=reports — returns one report's full metadata; omit to list all).
url	string	optional	HTTPS endpoint to receive events (for action=webhook_add). Must be public HTTPS (private/loopback rejected).
events	array	optional	Event types to subscribe to (for action=webhook_add; default all): job.completed, job.failed, deck.completed, deck.partial, deck.failed.
webhook_id	string	optional	Webhook subscription id (for action=webhook_remove / webhook_test).
asset_id	string	optional	Image asset ID (for action=delete_asset). Logos are content-addressed/shared and are not deleted by this action.

Raw schema

{
  "type": "object",
  "properties": {
    "action": {
      "type": "string",
      "enum": [
        "status",
        "usage",
        "jobs",
        "job",
        "download_url",
        "feedback",
        "feedback_list",
        "onboarding",
        "topup",
        "brand_report",
        "reports",
        "webhooks",
        "webhook_add",
        "webhook_remove",
        "webhook_test",
        "security_status",
        "delete_job",
        "delete_asset"
      ],
      "description": "Operation (required). feedback → report a defect or request against a render; pass job_id so it is actionable, and ask the user before filing. feedback_list → read YOUR OWN filed reports back, with `status` and the `resolution` written when one was acted on: check it before working around a defect you reported earlier, because it may already be fixed. brand_report → the per-token fidelity report for one of your brand kits (pass theme_id). topup → mints a Stripe checkout link the user pays at directly (wallet credits automatically) — use when a render is refused for balance. reports → list report types; webhook_add registers a push endpoint instead of polling — see the url/events props. delete_job is irreversible. delete_asset is irreversible for user-owned image assets."
    },
    "job_id": {
      "type": "string",
      "description": "Job ID (for action=job, action=download_url and action=delete_job)"
    },
    "limit": {
      "type": "integer",
      "description": "Max rows (action=jobs default 10; action=feedback_list default 50, max 100)"
    },
    "status": {
      "type": "string",
      "description": "Filter — action=jobs: queued/generating/complete/failed; action=feedback_list: open/resolved"
    },
    "include_children": {
      "type": "boolean",
      "description": "For action=jobs: include deck child slides (each carries parent_deck_id) so a deck's slides are discoverable by listing. Default false (parents only). Deck rows roll child cost up to the deck."
    },
    "message": {
      "type": "string",
      "description": "What went wrong or what you want, in the user's own words (for action=feedback)."
    },
    "category": {
      "type": "string",
      "enum": [
        "layout",
        "typography",
        "contrast",
        "content",
        "icons",
        "images",
        "theme",
        "chrome",
        "consistency",
        "bug",
        "feature_request",
        "testimonial",
        "general",
        "other"
      ],
      "description": "Feedback category (action=feedback to file under it, action=feedback_list to filter by it). The first nine are slide-quality categories — pair them with job_id."
    },
    "severity": {
      "type": "string",
      "enum": [
        "bug",
        "quality",
        "suggestion"
      ],
      "description": "For action=feedback: `bug` = it is broken, `quality` = it rendered but reads poorly, `suggestion` = a request. Defaults to suggestion, so file real defects explicitly or they are triaged as wishes."
    },
    "days": {
      "type": "integer",
      "description": "Lookback period (for action=usage, default 30)"
    },
    "amount": {
      "type": "number",
      "description": "USD top-up amount (for action=topup, default 10, min 10, max 1000). Volume bonus: $50→+10%, $100→+15%, $200→+20%."
    },
    "detail": {
      "type": "boolean",
      "description": "For action=status only: default false masks identity fields; true returns full email/user_id diagnostics for the authenticated user."
    },
    "include_preview": {
      "type": "string",
      "enum": [
        "none",
        "small",
        "default",
        "full"
      ],
      "description": "Preview (for action=job)"
    },
    "slug": {
      "type": "string",
      "description": "Report slug (for action=reports — returns one report's full metadata; omit to list all)."
    },
    "url": {
      "type": "string",
      "description": "HTTPS endpoint to receive events (for action=webhook_add). Must be public HTTPS (private/loopback rejected)."
    },
    "events": {
      "type": "array",
      "items": {
        "type": "string"
      },
      "description": "Event types to subscribe to (for action=webhook_add; default all): job.completed, job.failed, deck.completed, deck.partial, deck.failed."
    },
    "webhook_id": {
      "type": "string",
      "description": "Webhook subscription id (for action=webhook_remove / webhook_test)."
    },
    "asset_id": {
      "type": "string",
      "description": "Image asset ID (for action=delete_asset). Logos are content-addressed/shared and are not deleted by this action."
    }
  },
  "required": [
    "action"
  ]
}

README.md16 KBView on GitHub

mcp-name: dev.slideforge/slideforge

SlideForge MCP — PowerPoint slides for AI agents

SlideForge (slideforge.dev) — the deterministic PowerPoint compiler for AI agents. Typed slide intents → native, fully editable .pptx in under a second, with a fidelity manifest that states exactly what was bound verbatim. Built by Smart Data Brokers GmbH, Switzerland.

Remote MCP server + REST API. No local install, no Python environment, no python-pptx boilerplate. OAuth 2.1 for Claude Desktop & ChatGPT; API key for everything else.

smithery badge

⚠️ Disambiguation

"SlideForge" is used by multiple unrelated projects. This is SlideForge by Smart Data Brokers GmbH at slideforge.dev. Not affiliated with:

slideforge.io — a separate AI presentation generator
slideforge.fr — a French document polishing service
blink.new/p/slideforge-app — an unrelated web app
Other github.com/*/SlideForge repositories outside the smartdatabrokers org

When citing or linking, prefer slideforge.dev or "SlideForge by Smart Data Brokers."

Why SlideForge

A compiler, not a generator. A slide is a typed intent: pick a form from 200+ catalog patterns (KPI dashboards, waterfalls, Gantt plans, org charts, funnels, …), put your real content in typed fields. A deterministic engine lays it out — no LLM in the render path, same input → same slide, sub-second.
The honesty layer. Every response carries a fidelity manifest: per field, was your content bound verbatim, mixed, or ai_completed? A partial grade means some supplied content didn't make it onto the slide — the manifest names what was dropped; never deliver a partial render without telling the user what's missing. Slides with blocking defects don't bill (usable-or-free). If your agent feeds numbers into slides, this is what makes the output auditable.
Native, editable .pptx. Real shapes and text boxes — not images, not HTML exports. Openable and editable in PowerPoint.
Escape hatch included — under the same trust contract. mode=code runs your own python-pptx in a sandbox (widget/chart toolkit, theme injected, intent fields render as chrome). Code renders are linted, measured (layout block + presentation_ready), and provenance-checked — agents may escape the layout grammar, never the trust grammar.
Your template, natively. Upload your company's .pptx — slides are built ON your file (theme, masters, fonts), not a color-matched imitation.
Check for free. dry_run validates any payload + forecasts fidelity at $0 — or use mode=safe to validate-then-render in ONE call (renders + bills only if faithful; else a $0 report with the fix). verify tiers on code renders (lint default, lint+vlm adds a visual second-look). quality_profile (executive/technical/appendix) sets the readiness bar the layout is judged against — answered on any form. Free deck inspect (POST /v1/inspect) runs a deterministic quality report on any pptx.
97% quality parity with Gamma in our own blind side-by-side benchmark (internal instrument, not third-party).

Pricing in one breath: creating a slide 5¢ · transforming a slide 2¢ (translate, repair) · checking free. 60 free slides on signup, no subscription. slideforge.dev/pricing

Quick Start

One click, no config file:

VS Code (Copilot agent mode) signs you in over OAuth on first use — no key, no JSON file.

Cursor installs with an API-key placeholder: after clicking, replace sf_live_YOUR_KEY in the server's headers with a real key from the console. Cursor's own OAuth browser launch is broken as of 3.16.17, so the key is the working path there today.

Claude Code

bash

claude mcp add --transport http slideforge https://api.slideforge.dev/mcp/

Then just ask: "Make a KPI dashboard slide: revenue $12.4M (+18% YoY), 847 new clients, NPS 62."

Optional — install the skills + bundled server config as a plugin:

code

/plugin marketplace add smartdatabrokers/slideforge-mcp
/plugin install slideforge@slideforge-mcp

Or copy any folder from skills/ into ~/.claude/skills/ (personal) or .claude/skills/ (project).

Claude Desktop (OAuth — no key needed)

Settings → Connectors → Add custom connector → https://api.slideforge.dev/mcp/ — sign in with Google on first use.

ChatGPT (Developer Mode)

Settings → Apps → Advanced → Developer mode → Add custom connector → https://api.slideforge.dev/mcp/ (OAuth).

Cursor / Windsurf / Codex CLI / any MCP client (API key)

json

{
  "mcpServers": {
    "slideforge": {
      "url": "https://api.slideforge.dev/mcp/",
      "transport": "streamable-http",
      "headers": { "Authorization": "Bearer sf_live_YOUR_KEY" }
    }
  }
}

Get a key: slideforge.dev → Console → API keys. (Codex CLI and other AGENTS.md-native tools: see AGENTS.md.)

Run it locally (stdio — for container/offline clients)

Most clients should use the hosted remote server above (no install). But if your client boots MCP servers from a container or a local stdio process, run the bundled local server. It's a thin REST client over api.slideforge.dev — it holds no engine logic; the tool schemas are baked in locally (so discovery works offline, no key) and each call forwards to the SlideForge REST API authenticated with your key.

bash

pip install slideforge-mcp        # or: uv pip install slideforge-mcp
export SLIDEFORGE_API_KEY=sf_live_YOUR_KEY
slideforge-mcp                    # speaks MCP over stdio

Or via Docker:

bash

docker build -t slideforge-mcp .
docker run -i -e SLIDEFORGE_API_KEY=sf_live_YOUR_KEY slideforge-mcp

Client config (stdio):

json

{
  "mcpServers": {
    "slideforge": {
      "command": "slideforge-mcp",
      "env": { "SLIDEFORGE_API_KEY": "sf_live_YOUR_KEY" }
    }
  }
}

Schema discovery (tools/list) needs neither a key nor network; tool calls need the key.

LangChain / LlamaIndex (agent frameworks)

No SlideForge SDK needed — both load the MCP tools directly:

bash

pip install langchain-mcp-adapters      # or: pip install llama-index-tools-mcp

python

from langchain_mcp_adapters.client import MultiServerMCPClient
client = MultiServerMCPClient({"slideforge": {
    "transport": "streamable_http",
    "url": "https://api.slideforge.dev/mcp/",
    "headers": {"Authorization": f"Bearer {API_KEY}"}}})
tools = await client.get_tools()        # 7 tools, drop into any LangGraph agent

Runnable examples + the LlamaIndex equivalent: examples/. Need a key? Sign up — 60 free slides, no credit card — then grab it at console/keys.

REST (no MCP)

bash

curl -X POST https://api.slideforge.dev/v1/render/intent \
  -H "Authorization: Bearer sf_live_YOUR_KEY" \
  -H "Content-Type: application/json" \
  -d '{"form": "kpi_metrics", "headline": "Q3 at a glance",
       "data": {"metrics": [{"label": "Revenue", "value": "$12.4M", "delta": "+18% YoY"},
                             {"label": "New clients", "value": "847"},
                             {"label": "NPS", "value": "62"}]}}'

Full REST reference: slideforge.dev/docs/api

The 7 MCP tools

Tool	What it does	Cost
`create_slide`	ONE slide from a structured intent (form + typed fields) or a brief; `mode=safe` validates-then-renders in one call; `mode=code` for sandboxed python-pptx (verify tiers, chrome fields, patch-by-replacements). Routing controls: `variant`, `variant_policy`, `allow_fabrication`/`allow_truncation`/`allow_low_confidence` (honest defaults: reject at $0 rather than guess). `min_font_pt` sets a BINDING type floor — text grows to meet it where the box allows; content that cannot fit returns a $0 `min_font_not_met` error naming the size it needs. Response carries the fidelity manifest + a measured `layout` readiness block on diagram forms. Default themes ship topical design — a subject-informed palette + designed cover, named in the response's design note (`styling: "clean"` opts out; your pinned/uploaded brand theme always wins).	$0.05 (usable-or-free)
`create_deck`	Whole deck: `slides[]` of intents (code-mode slides are first-class children), parallel render, one merged .pptx, per-slide fidelity rollup + per-slide child jobs (own preview/pptx). Failed slides isolated + free; deck-level `dry_run` validates the whole deck at $0. Deck-level `language`, `direction` (`rtl` for Arabic/Hebrew — typeset right-to-left, layout unmirrored + honestly warned), `imagery`/`imagery_tag`, `styling` and `logo_id` inherit into every slide; a slide's own value wins.	N × $0.05
`plan_slide`	Brief → top form/variant candidates with confidence.	Free
`browse_catalog`	200+ patterns with per-form JSON Schemas + copy-pasteable example intents, themes, the code-mode widget toolkit. Pass an uploaded `theme_id` to list its branded cover/agenda/divider layouts. `type=brands` lists your brand kits with their versions. 9 built-in themes + your uploaded brand kits.	Free
`translate_deck`	Translate any PPTX preserving formatting (32 languages).	$0.02/slide
`upload_asset`	Logos, brand template PPTX, images; `purpose=pdf` extracts a PDF into editable slide intents (PowerPoint/Keynote/Google-Slides/Beamer-exported PDFs only — other sources aren't supported yet); or AI-generate an image. Brand template upload (`purpose=brand` — `purpose=theme` is the same thing under its old name, still accepted) renders NATIVE by default — decks are built on the client's own template file. Omit `data` on large files for an in-card drag/drop zone.	Free / $0.01/page / $0.05/image
`manage_account`	Balance, usage, jobs, security status, feedback, `action=feedback_list` to read your filed reports back, `action=brand_report` for a brand kit's per-token fidelity report.	Free

dry_run: true on create tools = validation + fidelity forecast at $0.

Two more tools (generate_report, manage_connections — data-driven reports from connected tools like Zoho Sprints) exist behind an enterprise gate and are not served by default.

Also on REST (for now): the Deck Doctor. POST /v1/inspect — a free deterministic Deck Quality Report for any pptx (overflow via real font metrics, content hidden behind shapes, off-canvas leftovers, WCAG contrast). POST /v1/repair — deterministic fixes, never your words, $0.02/repaired slide, free dry-run quote. Docs

Brand kits

A brand kit is your org's identity — colors, type, logo, and (optionally) an uploaded .pptx/.potx/.thmx template — stored under a slug and rendered against on every call.

Use one: pass theme_id=<slug> to create_slide/create_deck for the kit's default version, or <slug>@<n> to pin a specific version.
Create one: upload_asset(purpose="brand", data=<base64 .pptx/.potx/.thmx>) — decks then render NATIVE, built on your own template file. (purpose="theme" is the same path under its old name and still works.)
Discover: browse_catalog(type="brands") lists your kits with their versions.
Check fidelity: manage_account(action="brand_report", theme_id=<slug>) returns the per-token fidelity report for a kit.
Export or import from a URL: full kit CRUD, DTCG tokens.json/.potx/.thmx export, and importing an identity straight from a company's domain are REST-only today — /v1/brands (not yet mirrored as MCP tools).

Security

Tool result bodies are credential-free — no signed URLs in responses. Previews are embedded inline (the agent looks at the PNG directly); the .pptx downloads via header-auth (Authorization: Bearer + ownership check), not a bearer-in-URL.
Need a shareable link instead? POST /v1/jobs/<job_id>/download-url mints a short-TTL, single-use, revocable link.
Artifacts auto-delete 30 days after creation.
Every download is audit-logged.
manage_account(action=security_status) discloses the full posture in-band.

Agent skills (this repo)

Copy-in skills that teach an agent to use SlideForge well — see skills/:

Skill	Teaches
`create-slide`	Intent-first slide/deck creation, schema discovery, dry-run, fidelity manifest, headless preview
`inspect-repair`	Free Deck Quality Report on any pptx + deterministic repair
`translate-pptx`	Format-preserving PPTX translation
`pdf-to-pptx`	PDF → editable PPTX extraction

For Codex CLI / Cursor / Copilot and other AGENTS.md-native tools, AGENTS.md carries the same guidance in the portable format. CLAUDE.md imports it for Claude Code.

Headless usage (Claude Code / Codex CLI)

No inline widgets in a terminal, but the tool result already embeds the preview PNG inline — the agent reads it directly out of the response, no fetch needed. The .pptx downloads via header-auth:

bash

curl -H "Authorization: Bearer sf_live_YOUR_KEY" \
  -o deck.pptx https://api.slideforge.dev/v1/jobs/<job_id>/pptx   # ownership-checked

To hand off a shareable link instead of the raw file, mint a single-use one: POST /v1/jobs/<job_id>/download-url — short-TTL, revocable, works once.

The self-review loop (render → view inline preview → fix → re-render) is documented in examples/claude-code.md.

How it compares

	SlideForge	python-pptx	Prompt-only AI decks
Editable native .pptx	✅	✅	often images/exports
Deterministic (same input → same slide)	✅	✅ (your code)	❌
States what was AI-touched (fidelity manifest)	✅	n/a	❌
Layout quality without hand-coding	✅ 200+ patterns	❌ DIY	varies
Hosted, agent-native (MCP + REST)	✅	❌ local	partial
Free pre-flight validation	✅ dry_run	n/a	❌

License

MIT (this repo: skills, examples, docs). The SlideForge service itself is a commercial API.

Install

Tools (7)

browse_catalogplan_slidecreate_slidecreate_decktranslate_deckupload_assetmanage_account

Configuration

Environment variables

SLIDEFORGE_API_KEYsecret

SlideForge API key (starts with sf_live_). Required to run tool calls; schema discovery works without it. Get one at https://slideforge.dev.

Add to VS Code Add to Cursor

claude_desktop_config.json

json

{
  "mcpServers": {
    "slideforge": {
      "command": "uvx",
      "args": [
        "slideforge-mcp"
      ],
      "env": {
        "SLIDEFORGE_API_KEY": "<YOUR_SLIDEFORGE_API_KEY>"
      }
    }
  }
}

SlideForge

SlideForge MCP — PowerPoint slides for AI agents

🛠️ Key Features

🚀 Use Cases

⚡ Developer Benefits

⚠️ Limitations

Topics

browse_catalog

plan_slide

create_slide

create_deck

translate_deck

upload_asset

manage_account

SlideForge MCP — PowerPoint slides for AI agents

⚠️ Disambiguation

Why SlideForge

Quick Start

Claude Code

Claude Desktop (OAuth — no key needed)

ChatGPT (Developer Mode)

Cursor / Windsurf / Codex CLI / any MCP client (API key)

Run it locally (stdio — for container/offline clients)

LangChain / LlamaIndex (agent frameworks)

REST (no MCP)

The 7 MCP tools

Brand kits

Security

Agent skills (this repo)

Headless usage (Claude Code / Codex CLI)

How it compares

Links

License

Install

Configuration

Related servers