# Fix list: Figma API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/figma-mcp, the October 2026 research run, assessed 1 October 2026. Grade B, 66.1 out of 100. This is everything the published grade says the listing lacks, the biggest possible gain to the total first. It comes from the reason given for each score, the checklist each category was scored against (https://www.anchorterminal.com/benchmark/#checklist), the provenance checks, the deductions, what we couldn't check and what the review panel asked for. A fix counts at the next check, once it's public. For a coding agent working on Figma API + MCP: work through the items below in the product, its docs and its public pages. Each category gives the reason for its score, with the points each checklist item earned, and the checklist itself, so the gap is the items that earned less than their points. Change the product, not the wording, and keep a note of what you changed and where it's published. ## 1. Payments & pricing, 30 out of 100, up to 8.8 more on the total Why it scored 30: No x402 or other machine payment (0). Seat prices are public by plan, but MCP calls and the coming usage-based write tools have no per-call price (10 of 20). Starter is free with no card per the 30 September check, though View and Collab seats get only 20 MCP calls a month (20). A person signs up in a browser and approves OAuth, and only catalogue clients can connect (0). The checklist (https://www.anchorterminal.com/benchmark/#checklist-payments): The published rubric, also on the [x402 page](https://www.anchorterminal.com/x402/). - 40, a machine payment protocol (x402, MPP or L402) on the tool's own endpoints. 10 to 30 when it covers only some endpoints or only goes through a third party, and the note says which. - 20, per-call or per-unit pricing published without a login. 10 for public plan-only pricing, 0 for "contact sales" or prices behind a login. - 20, a free tier or trial that doesn't need a card. - 20, autonomous onboarding, meaning an agent can get access without a person signing up in a browser (keyless use, x402, a programmatic key API). Payment platforms and agent wallets rarely charge for their own API over a machine protocol, so the first line has steps for them, and the highest one that applies counts. 40 when x402, MPP or L402 runs on all their own endpoints, 30 when it runs on part of their own API, 25 when their merchants can accept one, 20 for running a facilitator, 15 for paying as a buyer, and 0 when the only protocol is their own. Merchant acceptance sits above a facilitator because the platform's own customers can charge agents through it, while a facilitator settles for sellers who wire up the protocol themselves. The counter-argument (a facilitator does more for the protocol as a whole) has a point. Each note says which step applied. Open-source software you run yourself is scored on its hosted or paid option if it has one. A free, self-hosted package with nothing to buy gets 20, 20 and 20 for the last three lines, and 0 to 40 for the first only if it ships a payment protocol. ## 2. Reliability, 59 out of 100, up to 8.2 more on the total Why it scored 59: Statuspage at status.figma.com with history, read from its RSS feed (20). Three incidents since 3 July. File editing blocked for some users for about 43 minutes on 27 July, MCP tools unavailable for about 4 hours on 26 August, and a broad disruption from an AWS dependency for about 90 minutes on 27 September. Two majors (5 of 30). Published limits for REST by tier, seat and plan, and for MCP by seat (Dev and Full up to 200 calls a day and 10 a minute on Professional, 600 a day and 20 a minute on Enterprise) (15). REST 429s carry `Retry-After` per the 30 September check. No idempotency guidance for comment or variable writes (12 of 15). No SLA found (0). REST is GA, and the MCP canvas write tools are in beta (7 of 10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-reliability): Hosted APIs, MCP servers, models and platforms. - 20, a public status page with component history (Statuspage, Instatus, BetterStack or the vendor's own). - 0 to 30, the incident record for the last 90 days on that page. 30 for a clean record or trivial incidents only, 20 for minor incidents only, 10 for one major outage (an hour or more of a core API down, or errors across the board), 0 for several. 5 when there's no history we could read, and the note says so. - 15, rate limits documented with numbers. - 15, documented 429 or overload handling (Retry-After, backoff guidance), and idempotency keys or safe-retry guidance where writes are involved. - 10, an SLA published for any paid tier. - 10, the surface agents use is generally available, not beta or preview. Local packages, SDKs, frameworks and stdio MCP servers. - 20, installs from an official package with supported runtimes stated. - 25, a public CI and test suite, passing on the default branch. - 0 to 25, open crash or regression issues relative to activity (25 for few and handled, 0 for many, old and unanswered). - 15, semver discipline and breaking changes called out in a changelog. - 15, version 1.0 or later, or declared stable. Protocols are read from their reference implementations, the public facilitators or servers, spec stability and test vectors. ## 3. Agent ergonomics, 60 out of 100, up to 6.5 more on the total Why it scored 60: REST file reads can be cut down with `ids` and `depth`. The MCP server lists 35 tools across read, write and Weave groups, with some remote-only and others desktop-only, and we found no toolsets or read-only subset (15 of 25). Cursor pagination on comments, versions and folders (16 of 20). REST errors carry a status and message (13 of 20). We couldn't confirm readOnlyHint or destructiveHint on the closed MCP server, and REST writes have no idempotency keys. `weave_run_tool` stops with `cost_confirmation_required` until the caller acknowledges the credit cost (8 of 20). TypeScript types for REST and the Code Connect CLI, but no official REST client in two languages (8 of 15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-ergonomics): - 0 to 25, context cost. For MCP, the number and size of the tool definitions (25 for ten or fewer compact tools, 15 for 11 to 30, 5 for more than 30, plus up to 10 back for toolsets, dynamic loading or read-only subsets). For APIs, whether responses can be sized (field selection, limits, summaries). - 20, pagination, filtering and output-size controls. - 20, actionable, documented error responses, codes and messages an agent can recover from. - 20, idempotency or safe retries, and for MCP the `readOnlyHint` and `destructiveHint` annotations. - 15, sensible defaults, few required parameters, and official SDKs in at least two languages. Models are read for tool use, structured output, prompt caching, context length, batch and SDKs. Frameworks for how much code and how many defaults a tool-calling agent with MCP needs. ## 4. Security & auth, 74 out of 100, up to 4.6 more on the total Why it scored 74: OAuth 2 with per-resource scopes such as `file_content:read` and `file_comments:write`, scoped personal access tokens, and plan access tokens with resource allowlists and expiry of up to a year. The MCP server signs in with OAuth and only catalogue-listed clients can connect (30). Read-only scopes give least privilege on REST. The MCP server has no documented read-only mode, and canvas writes such as `use_figma` run without a confirmation step (13 of 20). File content, layer names and comments written by collaborators reach the model as they are, and we found no prompt-injection guidance (3 of 15). Activity logs and an AI usage API for Enterprise (12 of 15). SOC 2 Type 2, SOC 3, ISO/IEC 27001, 27017, 27018 and 27701 and FedRAMP on the security page. We couldn't read security.txt or confirm a bug bounty (16 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-security): - 0 to 30, the credential model. 30 for OAuth 2.1 with scopes, or scoped and revocable keys with rotation. 20 for plain revocable API keys. 10 for one all-powerful key. 10 off when a secret can travel in a URL query string as a documented option. - 0 to 20, read-only or least-privilege modes, and confirmation or approval for destructive actions. - 0 to 15, prompt-injection posture where the tool returns untrusted content (documented mitigations or guidance). A tool that returns no untrusted content gets 10. - 0 to 15, audit logs or per-call visibility for the operator. - 0 to 20, a security programme. security.txt or a disclosure policy, a bug bounty, SOC 2 or ISO 27001, advisories handled in public. Models are read for retention, whether API data trains models (and whether that's off by default), zero-retention options and certifications. Frameworks for telemetry defaults, approval hooks, guardrails and sandboxing. ## 5. Schema & documentation, 86 out of 100, up to 2.3 more on the total Why it scored 86: Public OpenAPI spec in figma/rest-api-spec, with TypeScript types on npm (25). llms.txt at developers.figma.com (10). The MCP tools page explains each tool and splits read, write and Weave groups, but the server is closed, so we couldn't read its own tool definitions (13 of 20). Typed parameters with enums such as image `format` (png, jpg, svg, pdf) and `depth` limits (13 of 15). Reference examples throughout. We didn't read an error catalogue (10 of 15). A dated REST changelog with deprecation notices and v1 and v2 paths (15). The checklist (https://www.anchorterminal.com/benchmark/#checklist-schema): APIs and MCP servers. - 25, a machine-readable contract (a public OpenAPI file or similar; for MCP, typed JSON Schema inputs on every tool). - 10, llms.txt or Markdown docs served for agents. - 0 to 20, descriptions that say what a tool is for, when to use it and when not to, read from the tool definitions in the source or the API reference. - 0 to 15, typed inputs with enums, constraints and required fields, and no free-form JSON blobs. - 0 to 15, examples and documented error responses. - 15, versioning and a public changelog. Models are read from the API reference, the OpenAPI file, llms.txt, the structured-output and tool-use docs and the model cards. Frameworks from docs a model can follow, typed interfaces, examples and the API reference. ## 6. Transparency & trust, 75 out of 100, up to 2.2 more on the total Made of editorial 59, provenance 90. Why it scored 75: Closed service under published terms (15). The privacy policy says customer content trains Figma's AI models when 'Content Training' is on in admin settings, keeps data 'for as long as you use our Services', and stores it in the United States. A customer DPA is referenced (15 of 30). Dated deprecation notices, such as the v1 projects endpoints on 10 August 2026, but no removal dates (13 of 20). A sub-processors page and US data location (16 of 20). The checklist (https://www.anchorterminal.com/benchmark/#checklist-transparency): - 0 to 30, source availability and licence clarity. 30 for open source under an OSI licence, 15 for closed with clear terms, 0 for unclear terms. - 0 to 30, data handling and retention statements that agree with each other (privacy policy, DPA, retention periods, subprocessors). - 0 to 20, a deprecation policy or notices with dates. - 0 to 20, telemetry disclosed with an opt-out (local software), or subprocessors and data locations disclosed (hosted). The other half of Transparency and trust is the provenance score, computed from checked facts (below). The category score is the mean of the two. Provenance checks not met in full (half of this category, computed from checked facts): - security.txt: could not be fetched (0 of 10) ## 7. Maintenance & community, 84 out of 100, up to 1.4 more on the total Why it scored 84: REST changelog entry on 17 September 2026 and an MCP update on 24 September per the 30 September check (30). REST changelog entries on 23 July, 10 August and 17 September (20). Closed service with a public changelog and support. We didn't test support (12 of 15). com.figma.mcp/mcp is in the official registry under a DNS-verified namespace, latest 1.0.3 (15). @figma/rest-api-spec and Code Connect are maintained on npm. We didn't audit their dependencies (7 of 10). The checklist (https://www.anchorterminal.com/benchmark/#checklist-maintenance): - 0 to 30, time since the last release, or the last published model or API change for a closed service. 30 within 30 days, 20 within 90, 10 within 180, 0 older. - 20, at least three releases or dated changelog entries in the last 90 days. - 0 to 25, responsiveness. Issues and pull requests answered on GitHub (the open issues and how recent the replies are). For closed services, a public changelog and a support or community channel that answers, 0 to 15. - 15, presence in the official MCP registry under a verified namespace (MCP servers), or current official SDKs (APIs and models). - 10, package health, current dependencies and CI. Models are read for deprecation notice periods and model churn rather than release counts. ## What we couldn't check What we couldn't read counted as absent. Publishing it on a page a plain HTTP fetch can read (not only in a browser) lets the next check count it. - MCP tool annotations and schemas; the server is closed and we couldn't call tools/list. - Whether Figma runs a public bug bounty; security.txt on figma.com isn't readable to automated fetches. - Whether canvas write tools are still free and when usage pricing starts; we didn't fetch the pricing page this run. - REST error catalogue and 429 headers, taken from the 30 September check rather than re-read. ## Weaknesses - View and Collab seats get 6 MCP calls a month on paid plans - MCP tools were unavailable for about 4 hours on 26 August 2026 - Only clients in Figma's MCP catalogue can connect - No prompt-injection guidance for file content and comments - No machine payment, and no per-call price for MCP or the coming paid write tools ## What costs an agent a turn today The notes we give agents before they call it. Each one is a workaround an agent shouldn't need. - Pass `ids=` and `depth=` to `GET /v1/files/:key`. A whole file is large - `GET /v1/images/:key` renders nodes to PNG, JPG, SVG or PDF and returns short-lived URLs - On 429 read `Retry-After`. Limits are per user and app for OAuth, per user for personal tokens and per token for plan tokens - Use the v2 folders endpoints. The v1 projects endpoints were deprecated on 10 August 2026 - Confirm the credit cost with the user when `weave_run_tool` returns `cost_confirmation_required` ## What the review panel asked for - Open MCP to any client - Idempotency keys on writes - Publish MCP tool schemas - Publish an error catalogue ## When it's done Send what changed and where it's published as a dispute (https://www.anchorterminal.com/builders/#disputes, or `POST https://www.anchorterminal.com/api/v1/contact` with `"kind": "dispute"`). Disputes are answered in public, and the listing is checked again by the same checklist. Paying for an audit or a listing claim changes nothing here.