# Fix list: Miro API + MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/miro, the October 2026 research run, assessed 1 October 2026. Grade B, 65.3 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 Miro 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 machine payment protocol (0). Seat prices are public by plan and MCP calls are capped per plan, with no per-call price (10 of 20). Free plan with 3 editable boards, the REST API and 100 MCP calls a day, no card per the 30 September check (20). A person creates the OAuth app or approves the MCP sign-in in a browser (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. Agent ergonomics, 63 out of 100, up to 6 more on the total Why it scored 63: 18 MCP tools, in the 11 to 30 band, and `canvas_read_as_svg` returns a whole board as SVG, which can be large (15 of 25). REST lists page with `limit` and `cursor` and filter by item type, and `board_search_boards` finds boards over MCP (18 of 20). Errors carry a machine code and message (16 of 20). We couldn't confirm readOnlyHint or destructiveHint on the closed MCP server, and REST creates have no idempotency key (6 of 20). The official Node client, @mirohq/miro-api 2.2.4, was last published on 5 February 2025 (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. ## 3. Reliability, 73 out of 100, up to 5.4 more on the total Why it scored 73: incident.io status page with regional dashboards for the EU, US, Australia and Japan, and history (20). Since July the history lists intermittent registration and login problems on 31 August and username-and-password sign-in unavailable on 9 September, with no API or board incidents and no durations shown (20 of 30). REST limits are published as credits, 100,000 a minute with calls costing 50 to 2,000 credits by level, and MCP calls are capped per day by plan (15). 429s return a JSON body with `code: tooManyRequests` and `X-RateLimit-Limit`, `-Remaining` and `-Reset` headers, and the docs advise exponential backoff. No `Retry-After` and no idempotency guidance for creates (10 of 15). No SLA found (0). REST v2 is GA. We didn't see a beta label on the MCP tools page, but didn't confirm the server's status either (8 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. ## 4. Security & auth, 70 out of 100, up to 5.3 more on the total Why it scored 70: REST uses OAuth 2.0 apps with scopes such as `boards:read`, `boards:write`, `team:read` and `identity:read`, which are coarse. The MCP server uses OAuth 2.1 with dynamic client registration and sees only boards the user can already open (25 of 30). A `boards:read` token gives read-only REST access. The MCP server has no read-only mode, though its 18 tools include no delete, and Enterprise admins must switch MCP on (13 of 20). Sticky notes, comments and board text written by collaborators reach the model through `canvas_read_as_svg` and `comment_list_comments`, and we found no prompt-injection guidance (3 of 15). The trust site describes audit logs that record AI interactions (12 of 15). ISO/IEC 27001:2022, ISO/IEC 42001:2023, SOC 2 Type II, SOC 3, Cyber Essentials, a public bug bounty and security@miro.com. No security.txt per the 30 September check (17 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, 85 out of 100, up to 2.4 more on the total Why it scored 85: OpenAPI spec in miroapp/api-clients per the 30 September check (25). llms.txt at developers.miro.com (10). The MCP tools page lists all 18 tools and a `canvas_get_canvas_composer_skill` tool hands the model drawing guidance, but the server is closed and we couldn't read its tool definitions (12 of 20). REST inputs are typed, while the MCP canvas tools take whole SVG documents as strings (10 of 15). REST errors share one documented shape (`status`, `code`, `message`, `context`, `type`), with examples across the reference (13 of 15). Dated changelog with an RSS feed and a versioned v2 API (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. Maintenance & community, 77 out of 100, up to 2 more on the total Why it scored 77: Changelog entry on 17 September 2026 (30). Five dated entries since 3 July, on 14 July, 12 and 19 August and 8 and 17 September (20). Closed service with a public changelog and a developer community. The miro-ai repository of plugins and skills had commits on 16 and 17 September (10 of 15). io.github.miroapp/mcp-server is in the official registry under a GitHub-verified namespace, latest 1.0.2, but the Node client hasn't had a release since February 2025 (13 of 15). Node client stale for 20 months (4 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. ## 7. Transparency & trust, 79 out of 100, up to 1.8 more on the total Made of editorial 67, provenance 90. Why it scored 79: Closed service under published terms. The miro-ai plugins and skills are MIT (17 of 30). The trust site says customer data is excluded from AI training and only opted-in, non-enterprise user data may be used, names data residency in Australia, the EU, the US and Japan, and lists subprocessors. We didn't read retention periods (22 of 30). Dated changelog notices, but the legacy MCP board tools got six days between the 8 September notice and the 14 September migration deadline (8 of 20). Subprocessors named, including AWS, Anthropic, OpenAI, Microsoft and Google, with four residency regions (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: not found (0 of 10) ## Deductions Each comes off the total. A fixed and documented problem counts for less at the next check. - -3: the changelog announced on 2026-09-08 that legacy MCP board tools would go, with a migration deadline of 14 September, and removed them on 2026-09-17. Notice was given, but nine days is short for a breaking change, so the lowest deduction (https://developers.miro.com/changelog.rss). ## 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. - Durations of the 31 August and 9 September login incidents; the history page doesn't show them. - MCP tool annotations and schemas; the server is closed. - Whether OAuth access tokens expire by default for REST apps. - Data retention periods; we read the trust site, not the privacy policy. ## Weaknesses - Legacy MCP board tools were removed nine days after the deprecation notice - No prompt-injection guidance for board content written by collaborators - OAuth scopes are coarse (`boards:read`, `boards:write`) - The official Node client hasn't been released since February 2025 - MCP daily caps are low on Free (100) and Starter (500) ## 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. - Create shapes first, then connectors with `startItem` and `endItem` ids - Put related items in a frame and set `parent` so they move together - Watch `X-RateLimit-Remaining`. There's no `Retry-After`, so back off exponentially on 429 - Through MCP, call `canvas_read_as_svg` before `canvas_update_from_svg` so the model sees the current layout - Don't call the legacy MCP board tools. They were removed on 17 September 2026 ## What the review panel asked for - Idempotency keys on creates - Retry-After on 429 - Publish MCP tool schemas ## 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.