Rank #3 of 8 in Design & Prototyping
Install
npm install @figma/code-connectShowcase


Try itExperimental
See what an agent can do with Figma before you ever sign up. Pick a story: recorded sessions replay real probe-harness transcripts; commands tagged live-capable can re-run against the real endpoint from our edge, right now (▶ run live — the exact same request, live and recorded lines always labeled); the live MCP handshake runs real requests from our edge, right now — including, where the server allows it, one real read-only tool call (bring your own key for auth-gated servers); sandboxed self-drive sessions are designed and gated (docs/TRY-IT.md).
$npx -y @figma/code-connect --versionrecorded session — replayed, not liveVerified integrations
Connections to other tracked products — hover a chip for the verbatim evidence quote behind it.
By theme — the product's score on each story themeBy theme
Agent design — stories about agent design in this arenaAgent designevidence →
Stories about agent design in this arena
Agenticness — how well agents can access and operate the productAgenticnessevidence →
How well agents can access and operate the product
Ai design — stories about ai design in this arenaAi designevidence →
Stories about ai design in this arena
Automation depth — how much of the product can run unattendedAutomation depthevidence →
How much of the product can run unattended
Collaboration multiplayer — stories about collaboration multiplayer in this arenaCollaboration multiplayerevidence →
Stories about collaboration multiplayer in this arena
Components design systems — stories about components design systems in this arenaComponents design systemsevidence →
Stories about components design systems in this arena
Dev handoff — stories about dev handoff in this arenaDev handoffevidence →
Stories about dev handoff in this arena
Openness — open source, data portability, and self-hosting storiesOpennessevidence →
Open source, data portability, and self-hosting stories
Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibilityevidence →
Stories about plugins extensibility in this arena
Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plansevidence →
Plan structure and value — what each tier costs and what it unlocks
Privacy posture — data-handling and privacy storiesPrivacy postureevidence →
Data-handling and privacy stories
Prototyping — stories about prototyping in this arenaPrototypingevidence →
Stories about prototyping in this arena
Vector editing — stories about vector editing in this arenaVector editingevidence →
Stories about vector editing in this arena
Versioning export — stories about versioning export in this arenaVersioning exportevidence →
Stories about versioning export in this arena
Story verdicts — every judged story with its evidenceStory verdicts
What’s free: 0 free · 1 paid · 0 enterprise · 36 not stated in evidence
Follow the green: where the map greys out is where Figma stops today. ✓ full · ~ partial · ! disputed · — none · n/a not applicable.
Agent design — stories about agent design in this arenaAgent design
Stories about agent design in this arena
Agenticness — how well agents can access and operate the productAgenticness
How well agents can access and operate the product
API surface
Drive the product through a documented public API
✓9/10
unlocks → API sandbox · Full data export
Subscribe to events via webhooks
✓7/10
Build against official SDKs
✓8/10
Issue scoped/least-privilege API credentials for an agent
~4/10
Connect an agent via an official MCP server
✓8/10
Download a machine-readable API spec (OpenAPI or equivalent)
✓8/10
unlocks → Interactive API docs
Rely on versioned APIs with a documented deprecation policy
~3/10
Test against a sandbox environment without touching production data
—–
Explore an interactive API reference with runnable examples
—0/10
Docs for agents
Point an agent at llms.txt or agent-oriented docs
✓8/10
Agentic features
Delegate tasks to a built-in AI assistant inside the product
!5/10
Operate the product with natural-language commands
~5/10
Plug MCP servers into this product so it can use their tools
—–
Get AI-generated insights and suggestions from my data inside the product
!5/10
Set up automations that run autonomously in the background
~5/10
Ai design — stories about ai design in this arenaAi design
Stories about ai design in this arena
Automation depth — how much of the product can run unattendedAutomation depth
How much of the product can run unattended
Collaboration multiplayer — stories about collaboration multiplayer in this arenaCollaboration multiplayer
Stories about collaboration multiplayer in this arena
Components design systems — stories about components design systems in this arenaComponents design systems
Stories about components design systems in this arena
Design systems
Dev handoff — stories about dev handoff in this arenaDev handoff
Stories about dev handoff in this arena
Openness — open source, data portability, and self-hosting storiesOpenness
Open source, data portability, and self-hosting stories
Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibility
Stories about plugins extensibility in this arena
Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans
Plan structure and value — what each tier costs and what it unlocks
Privacy posture — data-handling and privacy storiesPrivacy posture
Data-handling and privacy stories
Prototyping — stories about prototyping in this arenaPrototyping
Stories about prototyping in this arena
Vector editing — stories about vector editing in this arenaVector editing
Stories about vector editing in this arena
Versioning export — stories about versioning export in this arenaVersioning export
Stories about versioning export in this arena
Sorted by importance (agentic first) (high → low) · 53/53 stories · click a row’s chevron for the rationale and evidence
Drive the product through a documented public API G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 9/10 | Tprobed | |
Connect an agent via an official MCP server G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | full | 8/10 | Tprobed | |
Delegate tasks to a built-in AI assistant inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | disputed | 5/10 | Dcontradicted | |
Plug MCP servers into this product so it can use their tools G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 3 | none | untested | none yet | |
Build against official SDKs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Download a machine-readable API spec (OpenAPI or equivalent) G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Point an agent at llms.txt or agent-oriented docs G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 8/10 | Tprobed | |
Subscribe to events via webhooks G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | full | 7/10 | Cclaimed | |
Get AI-generated insights and suggestions from my data inside the product G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | disputed | 5/10 | Dcontradicted | |
Operate the product with natural-language commands G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Xcommunity | |
Run the product headlessly / in CI for automation G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Cclaimed | |
Set up automations that run autonomously in the background G Agentic features | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Cclaimed | |
Use an official CLI G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 5/10 | Tprobed | |
Issue scoped/least-privilege API credentials for an agent G Agent access | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 4/10 | Cclaimed | |
Rely on versioned APIs with a documented deprecation policy G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | partial | 3/10 | Cclaimed | |
Explore an interactive API reference with runnable examples G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 2 | none | 0/10 | ||
Test against a sandbox environment without touching production data G Api quality | ai-native user | Agenticness — how well agents can access and operate the productAgenticness | 1 | none | untested | none yet | |
My coding agent can pull real design context — frames, variables, screenshots, component mappings — through an MCP server or API to implement the design C Agent ops | ai-native user | Agent design — stories about agent design in this arenaAgent design | 3 | full | 9/10 | Tprobed | |
My whole team can edit the same file simultaneously with live cursors and instant sync C Collaboration | designer | Collaboration multiplayer — stories about collaboration multiplayer in this arenaCollaboration multiplayer | 3 | full | 8/10 | Cclaimed | |
Inspect any layer and get measurements, styles, assets, and code snippets (CSS/iOS/Android) without an editor seat G Handoff | developer | Dev handoff — stories about dev handoff in this arenaDev handoff | 3 | partialpaid | 5/10 | Xcommunity | |
Define rules that trigger actions automatically on events G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 3 | partial | 4/10 | Cclaimed | |
I get professional vector tools — pen and path editing, boolean operations, precise alignment — for real interface design work C Canvas | designer | Vector editing — stories about vector editing in this arenaVector editing | 3 | partial | 4/10 | Cclaimed | |
Build reusable components with variants and per-instance overrides that stay linked to their source C Design systems | designer | Components design systems — stories about components design systems in this arenaComponents design systems | 3 | partial | 3/10 | Cclaimed | |
Export all of my data in open formats and leave G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | disputed | 3/10 | Dcontradicted | |
Self-host the core product G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 3 | none | 0/10 | ||
Prevent my data from being used to train AI models G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 3 | none | untested | none yet | |
An agent can create or modify designs programmatically — through a write-capable API, plugin surface, or MCP tools — not just read them C Agent ops | ai-native user | Agent design — stories about agent design in this arenaAgent design | 2 | full | 9/10 | Tprobed | |
Wire screens into clickable prototypes with triggers, transitions, and overlays — no code required C | designer | Prototyping — stories about prototyping in this arenaPrototyping | 2 | full | 9/10 | Xcommunity | |
A documented plugin API with typings and samples lets me build and distribute my own editor extensions C Plugins | developer | Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibility | 2 | full | 8/10 | Cclaimed | |
Manage design tokens or variables — colors, spacing, typography — with modes or themes applied across designs C Design systems | designer | Components design systems — stories about components design systems in this arenaComponents design systems | 2 | full | 8/10 | Cclaimed | |
Designs map to production code — component-to-code mappings or direct design-to-code output I can actually ship C Handoff | developer | Dev handoff — stories about dev handoff in this arenaDev handoff | 2 | partial | 7/10 | Xcommunity | |
Extend the editor from a large plugin community or marketplace — icons, data fillers, accessibility checkers, and more G Plugins | designer | Plugins extensibility — stories about plugins extensibility in this arenaPlugins extensibility | 2 | full | 7/10 | Xcommunity | |
An agent can render and export designs — screenshots, images, or production formats — through a documented programmatic surface C Agent ops | ai-native user | Agent design — stories about agent design in this arenaAgent design | 2 | partial | 6/10 | Tprobed | |
Comment directly on designs, mention teammates, and resolve threads so review happens in the file, not in email C Collaboration | product manager | Collaboration multiplayer — stories about collaboration multiplayer in this arenaCollaboration multiplayer | 2 | full | 6/10 | Cclaimed | |
Generate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually produces C Ai | designer | Ai design — stories about ai design in this arenaAi design | 2 | partial | 6/10 | Xcommunity | |
Do everything through the API that I can do in the UI G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | partial | 5/10 | Tprobed | |
Perform bulk operations across many items at once G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | partial | 5/10 | Xcommunity | |
Shared libraries publish components and styles across files and projects, with controlled updates when the source changes C Design systems | designer | Components design systems — stories about components design systems in this arenaComponents design systems | 2 | partial | 5/10 | Cclaimed | |
Export production assets — PNG, SVG, PDF, and more — with per-layer presets, scales, and slices C Files | designer | Versioning export — stories about versioning export in this arenaVersioning export | 2 | partial | 4/10 | Xcommunity | |
Full version history lets me name milestones, compare, and restore any earlier state of a file C Files | designer | Versioning export — stories about versioning export in this arenaVersioning export | 2 | partial | 3/10 | Cclaimed | |
Frames can behave responsively — auto layout, constraints, and grids resize designs the way real UIs flex C Canvas | designer | Vector editing — stories about vector editing in this arenaVector editing | 2 | partial | 2/10 | Cclaimed | |
Read the product's source under an open license G | ai-native user | Openness — open source, data portability, and self-hosting storiesOpenness | 2 | none | 0/10 | ||
Self-host the full design platform on my own infrastructure under an open-source license C Files | developer | Versioning export — stories about versioning export in this arenaVersioning export | 2 | none | 0/10 | ||
Choose where my data is stored (region/residency) G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Control data retention and deletion G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Opt out of telemetry and usage tracking G | ai-native user | Privacy posture — data-handling and privacy storiesPrivacy posture | 2 | none | untested | none yet | |
Schedule recurring jobs or workflows G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 2 | none | untested | none yet | |
The free tier supports real design work — usable editor and collaboration without a paid seat G Pricing | designer | Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans | 2 | none | untested | none yet | |
Built-in AI handles asset chores — image generation, background removal, content-aware fills, copy suggestions — inside the editor C Ai | designer | Ai design — stories about ai design in this arenaAi design | 1 | partial | 5/10 | Xcommunity | |
Prototypes can carry advanced behavior — animation between states, conditions or variables, scroll effects — to feel like the real product C | designer | Prototyping — stories about prototyping in this arenaPrototyping | 1 | partial | 5/10 | Cclaimed | |
Published plan pricing makes seat types, tiers, and AI-feature gating clear before procurement G Pricing | product manager | Pricing plans — plan structure and value — what each tier costs and what it unlocksPricing plans | 1 | partial | 5/10 | Cclaimed | |
Version, review, and roll back my automations G | ai-native user | Automation depth — how much of the product can run unattendedAutomation depth | 1 | partial | 4/10 | Cclaimed | |
The file format is open or documented, so my designs stay portable and toolable outside the vendor's editor C Files | developer | Versioning export — stories about versioning export in this arenaVersioning export | 1 | none | 0/10 |
Opportunities — the stories that would move this product's scores, from its own judged verdictsOpportunitiestop 8 of 36 stories with headroom
What would move Figma’s scores — derived from its own judged verdicts, biggest headroom first. Each line quotes what the judge found missing; shipping it (or evidencing it publicly) is the fix.
Agenticness — how well agents can access and operate the productPlug MCP servers into this product so it can use their tools
nonemoves agent-readyimpact 45
All MCP-related evidence describes Figma exposing its own MCP server for external clients (e.g., IDEs, coding agents) to consume Figma's tools — the opposite direction of this story, which asks whether Figma itself can plug in and use external MCP servers' tools.
Openness — open source, data portability, and self-hosting storiesSelf-host the core product
nonemoves PA Scoreimpact 30
Figma is a cloud SaaS product with no evidence of any self-hosted deployment option for the core design tool; evidence only covers cloud APIs, plugins, MCP server, and community complaints about proprietary lock-in (figma-comm-7), which actually underscores the lack of self-hosting.
Privacy posture — data-handling and privacy storiesPrevent my data from being used to train AI models
nonemoves PA Scoreimpact 30
No evidence pack items address AI training data opt-out or data usage controls for AI model training; nothing about privacy settings, data processing agreements, or opt-out toggles is mentioned.
Agenticness — how well agents can access and operate the productExplore an interactive API reference with runnable examples
nonemoves API qualityimpact 30
Figma's REST API docs describe endpoints and there's a separate OpenAPI spec repo, but no evidence shows an interactive reference with runnable/try-it-now examples; probes for standard openapi.json/swagger endpoints on the docs site returned 404s, and no docs mention interactive code sandboxes or live example runners.
Components design systems — stories about components design systems in this arenaBuild reusable components with variants and per-instance overrides that stay linked to their source
partialq3/10moves PA Scoreimpact 21
Missing: explicit documentation or examples of variant properties, instance override behavior, and how overrides remain linked to (and reset from) the main component.
Agenticness — how well agents can access and operate the productRely on versioned APIs with a documented deprecation policy
partialq3/10moves API qualityimpact 21
Missing: explicit deprecation policy statement, version support timelines, sunset/EOL notices for old endpoints.
Automation depth — how much of the product can run unattendedSchedule recurring jobs or workflows
nonemoves PA Scoreimpact 20
No evidence of any scheduling, cron-like, or recurring job/workflow automation capability in Figma's docs, API, webhooks, or MCP server offerings — webhooks are event-triggered, not scheduled recurring jobs.
Pricing plans — plan structure and value — what each tier costs and what it unlocksThe free tier supports real design work — usable editor and collaboration without a paid seat
nonemoves PA Scoreimpact 20
The evidence pack describes general Figma design/collaboration/prototyping capabilities (figma-docs-14, figma-docs-15, figma-docs-16) but nothing ties these specifically to the free tier vs.
Showing the top 8 of 36 — every none/partial verdict in the story verdicts table is headroom.
Think a verdict is wrong? Every verdicts-table row has a Flag link — see the methodology.
Coverage map — which docs area, API section, or community source covers which judged storiesCoverage map14 surfaces · 40 covered stories
Where the cited evidence behind each covered verdict came from — the same citations the verdicts table shows, no extra judging.
docs25 stories
- An agent can create or modify designs programmatically — through a write-capable API, plugin surface, or MCP tools — not just read them
- An agent can render and export designs — screenshots, images, or production formats — through a documented programmatic surface
- My coding agent can pull real design context — frames, variables, screenshots, component mappings — through an MCP server or API to implement the design
- Run the product headlessly / in CI for automation
- Connect an agent via an official MCP server
- Use an official CLI
- Drive the product through a documented public API
- Issue scoped/least-privilege API credentials for an agent
- Build against official SDKs
- Subscribe to events via webhooks
- Set up automations that run autonomously in the background
- Rely on versioned APIs with a documented deprecation policy
- Perform bulk operations across many items at once
- Define rules that trigger actions automatically on events
- Version, review, and roll back my automations
- Comment directly on designs, mention teammates, and resolve threads so review happens in the file, not in email
- My whole team can edit the same file simultaneously with live cursors and instant sync
- Manage design tokens or variables — colors, spacing, typography — with modes or themes applied across designs
- Shared libraries publish components and styles across files and projects, with controlled updates when the source changes
- Designs map to production code — component-to-code mappings or direct design-to-code output I can actually ship
- Inspect any layer and get measurements, styles, assets, and code snippets (CSS/iOS/Android) without an editor seat
- Do everything through the API that I can do in the UI
- Export all of my data in open formats and leave
- A documented plugin API with typings and samples lets me build and distribute my own editor extensions
- Extend the editor from a large plugin community or marketplace — icons, data fillers, accessibility checkers, and more
Hacker News12 stories
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Built-in AI handles asset chores — image generation, background removal, content-aware fills, copy suggestions — inside the editor
- Generate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually produces
- Perform bulk operations across many items at once
- Designs map to production code — component-to-code mappings or direct design-to-code output I can actually ship
- Inspect any layer and get measurements, styles, assets, and code snippets (CSS/iOS/Android) without an editor seat
- Export all of my data in open formats and leave
- Extend the editor from a large plugin community or marketplace — icons, data fillers, accessibility checkers, and more
- Wire screens into clickable prototypes with triggers, transitions, and overlays — no code required
- Export production assets — PNG, SVG, PDF, and more — with per-layer presets, scales, and slices
GitHub README9 stories
- My coding agent can pull real design context — frames, variables, screenshots, component mappings — through an MCP server or API to implement the design
- Use an official CLI
- Drive the product through a documented public API
- Build against official SDKs
- Download a machine-readable API spec (OpenAPI or equivalent)
- Rely on versioned APIs with a documented deprecation policy
- Designs map to production code — component-to-code mappings or direct design-to-code output I can actually ship
- Inspect any layer and get measurements, styles, assets, and code snippets (CSS/iOS/Android) without an editor seat
- A documented plugin API with typings and samples lets me build and distribute my own editor extensions
AI docs7 stories
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Built-in AI handles asset chores — image generation, background removal, content-aware fills, copy suggestions — inside the editor
- Generate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually produces
- Designs map to production code — component-to-code mappings or direct design-to-code output I can actually ship
- Published plan pricing makes seat types, tiers, and AI-feature gating clear before procurement
Design docs6 stories
- Comment directly on designs, mention teammates, and resolve threads so review happens in the file, not in email
- My whole team can edit the same file simultaneously with live cursors and instant sync
- Prototypes can carry advanced behavior — animation between states, conditions or variables, scroll effects — to feel like the real product
- Wire screens into clickable prototypes with triggers, transitions, and overlays — no code required
- Frames can behave responsively — auto layout, constraints, and grids resize designs the way real UIs flex
- I get professional vector tools — pen and path editing, boolean operations, precise alignment — for real interface design work
OpenAPI spec4 stories
developers.figma.com4 stories
- Drive the product through a documented public API
- Download a machine-readable API spec (OpenAPI or equivalent)
- A documented plugin API with typings and samples lets me build and distribute my own editor extensions
- Extend the editor from a large plugin community or marketplace — icons, data fillers, accessibility checkers, and more
figma.com4 stories
- Get AI-generated insights and suggestions from my data inside the product
- Delegate tasks to a built-in AI assistant inside the product
- Operate the product with natural-language commands
- Generate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually produces
Hc docs4 stories
- Version, review, and roll back my automations
- Build reusable components with variants and per-instance overrides that stay linked to their source
- Shared libraries publish components and styles across files and projects, with controlled updates when the source changes
- Full version history lets me name milestones, compare, and restore any earlier state of a file
Pricing docs4 stories
- Shared libraries publish components and styles across files and projects, with controlled updates when the source changes
- Designs map to production code — component-to-code mappings or direct design-to-code output I can actually ship
- Inspect any layer and get measurements, styles, assets, and code snippets (CSS/iOS/Android) without an editor seat
- Published plan pricing makes seat types, tiers, and AI-feature gating clear before procurement
Make docs2 stories
Prototyping docs2 stories
Probe proofs — replayable recordings from the probe harnessProbe proofs
Replayable recordings from our probe harness — see the Prove-It protocol to submit one.
$npx -y @figma/code-connect --versionreproduced$ npx -y @figma/code-connect --version \|/-\|/-\|/-\|/-\|/-\|/2.0.1 \
$curl -si -X POST https://mcp.figma.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>'reproduced$ curl -si -X POST https://mcp.figma.com/mcp -H 'Content-Type: application/json' -d '<jsonrpc initialize>' HTTP/2 401 content-type: text/plain; charset=utf-8 content-length: 12 date: Mon, 14 Sep 2026 23:16:23 GMT server-timing: proxy;dur=10 x-figma-rest-api-request-id: 80338886-c8df-475b-a21f-c00a131ebc25 access-control-allow-origin: * access-control-allow-headers: Content-Type, X-Figma-[redacted], Authorization access-control-expose-headers: Retry-After, X-Figma-Plan-Tier, X-Figma-Rate-Limit-Type, X-Figma-Upgrade-Link vary: X-Figma-[redacted], Authorization cache-control: no-cache, no-store www-authenticate: Bearer resource_metadata="https://mcp.figma.com/.well-known/oauth-protected-resource",scope="mcp:connect",authorization_uri="https://api.figma.com/.well-known/oauth-authorization-server" x-content-type-options: nosniff x-cache: Error from cloudfront via: 1.1 e772230a2b03c1d3d61ef5473331452c.cloudfront.net (CloudFront) x-amz-cf-pop: SFO53-P10 alt-svc: h3=":443"; ma=86400 x-amz-cf-id: h9QV-a-2yfVNP2ghA6q0xvLOnPFcBzjgM7iNf7RM9Hvbsr_9RD70Og== strict-transport-security: max-age=31536000; includeSubDomains; preload Unauthorized
$curl -s https://raw.githubusercontent.com/figma/rest-api-spec/main/openapi/openapi.yaml | head -4reproduced$ curl -s https://raw.githubusercontent.com/figma/rest-api-spec/main/openapi/openapi.yaml | head -4 openapi: 3.1.0 info: title: Figma API version: 0.42.0
Claims vs evidence — vendor claims reconciled against independent verdictsClaims vs evidence
10 of 23 testable claims verified · 1 contradicted → integrity 35/100
37 distinct capability claims found in Figma’s own claimed-docs/GitHub materials, reconciled against our judge’s independent verdicts.
10
Verified
12
Unverified
1
Contradicted
15
Undersold
Verified (20)
“MCP client can create and modify native Figma content directly on the canvas”
An agent can create or modify designs programmatically — through a write-capable API, plugin surface, or MCP tools — not just read themfullproof ↗
“MCP client can create and modify native Figma content directly on the canvas”
“Select a Figma frame and generate code from it via MCP”
Designs map to production code — component-to-code mappings or direct design-to-code output I can actually shippartialproof ↗
“Select a Figma frame and generate code from it via MCP”
“Pull variables, components, and layout data into an IDE for design-system work”
My coding agent can pull real design context — frames, variables, screenshots, component mappings — through an MCP server or API to implement the designfullproof ↗
“Capture the live UI of a web app and send it into new or existing Figma files”
An agent can create or modify designs programmatically — through a write-capable API, plugin surface, or MCP tools — not just read themfullproof ↗
“Generate architecture diagrams and ERDs in FigJam from prompts, code, or structured input”
Generate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually producespartialproof ↗
“API lets you view/extract objects, layers, and properties, get usage data, and listen for events via webhooks”
Drive the product through a documented public APIfullproof ↗
“Dev Mode shows true-to-production code snippets sourced from your design system, not autogenerated code”
Inspect any layer and get measurements, styles, assets, and code snippets (CSS/iOS/Android) without an editor seatpartialproof ↗
“Build and share high-fidelity, no-code, interactive prototypes”
Wire screens into clickable prototypes with triggers, transitions, and overlays — no code requiredfullproof ↗
“A built-in Figma agent generates new design directions, diagrams, edits images, and searches files from prompts”
Generate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually producespartialproof ↗
“Plugins can automate tasks and add new functionality across workflows”
Extend the editor from a large plugin community or marketplace — icons, data fillers, accessibility checkers, and morefullproof ↗
“Code Connect links design-system components in code to their Figma counterparts”
Designs map to production code — component-to-code mappings or direct design-to-code output I can actually shippartialproof ↗
“MCP server turns a design into a code-backed prototype or production build”
“MCP server turns a design into a code-backed prototype or production build”
Designs map to production code — component-to-code mappings or direct design-to-code output I can actually shippartialproof ↗
“Advanced Dev Mode inspection plus an MCP Server for deeper code/design access”
Inspect any layer and get measurements, styles, assets, and code snippets (CSS/iOS/Android) without an editor seatpartialproof ↗
“Advanced Dev Mode inspection plus an MCP Server for deeper code/design access”
“OpenAPI spec and TypeScript types are published for the REST API”
Download a machine-readable API spec (OpenAPI or equivalent)fullproof ↗
“Figma Make turns prompts/ideas into working prototypes you can polish and ship”
Generate or edit designs from a natural-language prompt — first drafts, layouts, or full mockups the tool actually producespartialproof ↗
“MCP server provides tools for reading and writing designs, connecting to codebases, and building generative plugins/shaders”
Unverified (18)
“Plugin API supports read and write access, letting developers view, create, and modify file contents”
A documented plugin API with typings and samples lets me build and distribute my own editor extensionsfullproof ↗
“Publish and share components/styles across teams from a central library”
Shared libraries publish components and styles across files and projects, with controlled updates when the source changespartialproof ↗
“Multiple people can edit the same file simultaneously with live cursors and instant sync”
My whole team can edit the same file simultaneously with live cursors and instant syncfullproof ↗
“Teams can leave comments and use cursor chat to give feedback inside the file”
Comment directly on designs, mention teammates, and resolve threads so review happens in the file, not in emailfullproof ↗
“Layout tools, type tools, and other precision controls give full design control”
I get professional vector tools — pen and path editing, boolean operations, precise alignment — for real interface design workpartialproof ↗
“Create and manage webhooks to observe file events”
“Teams can purchase shared AI credits with pay-as-you-go or subscription options”
Published plan pricing makes seat types, tiers, and AI-feature gating clear before procurementpartialproof ↗
“Create precise animations and reusable motion systems that ship as dev-ready animations”
Prototypes can carry advanced behavior — animation between states, conditions or variables, scroll effects — to feel like the real productpartialproof ↗
“View a file's full version history”
Full version history lets me name milestones, compare, and restore any earlier state of a filepartialproof ↗
“Plan access tokens scope API access to an org/enterprise plan rather than a personal account”
Issue scoped/least-privilege API credentials for an agentpartialproof ↗
“Teammates and AI agents share the same workspace context to generate and refine designs together”
My whole team can edit the same file simultaneously with live cursors and instant syncfullproof ↗
“Code Connect can sync a design-system's source of truth to and from Figma”
Manage design tokens or variables — colors, spacing, typography — with modes or themes applied across designsfullproof ↗
“Get summary counts of how many instances of a library's components exist across all files”
Shared libraries publish components and styles across files and projects, with controlled updates when the source changespartialproof ↗
“Plan-scoped tokens support user-agnostic automation like CI/CD and logging without gating by one person”
Run the product headlessly / in CI for automationpartialproof ↗
“Variables REST API supports querying, creating, updating, and deleting variables”
Manage design tokens or variables — colors, spacing, typography — with modes or themes applied across designsfullproof ↗
“Requests can be made on behalf of other users rather than through a personal Figma account”
Issue scoped/least-privilege API credentials for an agentpartialproof ↗
“Unlimited files and projects are available for a single team on paid plans”
Published plan pricing makes seat types, tiers, and AI-feature gating clear before procurementpartialproof ↗
“Plugins can run immediately on invocation or require custom UI input from the user”
A documented plugin API with typings and samples lets me build and distribute my own editor extensionsfullproof ↗
Contradicted (2)
“A built-in Figma agent generates new design directions, diagrams, edits images, and searches files from prompts”
Delegate tasks to a built-in AI assistant inside the productdisputedproof ↗
“Teammates and AI agents share the same workspace context to generate and refine designs together”
Delegate tasks to a built-in AI assistant inside the productdisputedproof ↗
Undersold (15)
An agent can render and export designs — screenshots, images, or production formats — through a documented programmatic surfacepartialproof ↗
Point an agent at llms.txt or agent-oriented docsfullproof ↗
Set up automations that run autonomously in the backgroundpartialproof ↗
Operate the product with natural-language commandspartialproof ↗
Rely on versioned APIs with a documented deprecation policypartialproof ↗
Built-in AI handles asset chores — image generation, background removal, content-aware fills, copy suggestions — inside the editorpartialproof ↗
Perform bulk operations across many items at oncepartialproof ↗
Define rules that trigger actions automatically on eventspartialproof ↗
Build reusable components with variants and per-instance overrides that stay linked to their sourcepartialproof ↗
Do everything through the API that I can do in the UIpartialproof ↗
Frames can behave responsively — auto layout, constraints, and grids resize designs the way real UIs flexpartialproof ↗
Export production assets — PNG, SVG, PDF, and more — with per-layer presets, scales, and slicespartialproof ↗
Claims outside our story set (3)
Real capability claims found in Figma’s own materials, but no story in this arena’s taxonomy covers them yet — that’s feedback on the taxonomy, not a mark against the product.
“Retrieve code resources from Figma Make files to give an LLM context”
source ↗“Create private plugins and widgets to keep internal data confined to your org”
source ↗“SCIM API automates role changes for onboarding/offboarding from your identity provider”
source ↗
Business model
Free Starter plan, then per-seat Professional/Organization tiers priced by seat type (Dev, Full) and custom Enterprise contracts; AI features gated by plan tier.
pricing ↗Score trend
How this product’s scores have moved as evidence and verdicts are re-derived — a point per change, not per day.
Try Experimental
Run it in the microterminal →Recorded agent sessions — and a live MCP handshake where the vendor ships one.
Flag
⚑ Flag a verdictThink a verdict is wrong? Opens a prefilled GitHub issue — or use the ⚑ next to any verdict above.
For agents
Agent surface uptime MCP 100% · llms.txt 100% (30d, checked every 6h since Sep 8 '26)
