# Fix list: Mural MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/mural-mcp, the October 2026 research run, assessed 5 October 2026. Grade E, 42 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 Mural 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. Reliability, 35 out of 100, up to 13 more on the total Why it scored 35: Atlassian Statuspage at status.mural.co with 13 components and history, but none for MCP or the API (15). One incident in the last 90 days, marked major, on 4 August 2026, a 36-minute SAML SSO sign-in error for some users, which falls short of an hour-long core outage (20). No rate limits documented for the MCP server. The REST API's per-app and per-user limits aren't stated to apply (0). No 429 or retry guidance for MCP (0). The preview disclaimer says Mural's service levels don't apply (0). Public preview, not generally available (0). 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. ## 2. Agent ergonomics, 26 out of 100, up to 12 more on the total Why it scored 26: Tool count and definition size unknown, since the list is behind OAuth. Client-side tool allow-lists are the only subsetting Mural mentions (10). The 29 September 2026 update says large-board overviews load faster, with no documented paging or size controls (5). Release notes say write attempts explain when access is limited, and nothing more on errors (5). Edits land in normal undo history, and we couldn't read readOnlyHint or destructiveHint annotations (3). The mural must stay open in a foreground browser tab signed in to the same account, the server works on one mural at a time, and there's no SDK (3). 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. Schema & documentation, 30 out of 100, up to 11.4 more on the total Why it scored 30: The tool list needs an OAuth sign-in with a paid Mural account, so we read Mural's help article instead. MCP tools carry JSON Schema inputs by protocol, but Mural publishes no tool reference and the developer docs page linked from the server's sign-in app returns 404 (10). No llms.txt or Markdown docs. The help article renders only through a crawler view of a Salesforce page (0). The help article lists what the server can and can't do, which tells an agent when not to use it, but no per-tool descriptions are public (6). Input types and constraints unread (5). A prompt library and a troubleshooting section, no documented error responses (4). Registry version 1.0.0 and dated weekly release notes that mention MCP, no MCP changelog (5). 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. ## 4. Payments & pricing, 10 out of 100, up to 11.3 more on the total Why it scored 10: No x402, MPP or L402 (0). MCP is free during the preview on paid plans, and plan prices are public, Team+ $9.99 and Business $17 a member a month billed yearly, nothing per call (10). The Free plan is excluded from MCP, so there's no free route (0). Signup, plan purchase and OAuth consent all need a person (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. ## 5. Security & auth, 72 out of 100, up to 4.9 more on the total Why it scored 72: OAuth only, with PKCE (S256), dynamic client registration, a revocation endpoint and scopes murals:read, murals:write, rooms:read and workspaces:read in the server's own metadata. The assistant inherits the user's Mural permissions and there's no service account (28). A read scope exists and view-only murals stay read-only, but enablement is account-wide, and deletes run with no server-side confirmation, relying on the client's approval prompts and undo (12). Mural content and existing comments written by other collaborators come back to the model, and we found no injection guidance (4). MCP actions are recorded in the mural activity log and the audit log as the user's, marked 'with AI'. The audit log is an Enterprise feature (13). SOC 2 Type 2, SOC 3, ISO 27001 and ISO 42001, a disclosure page that routes to a private HackerOne bounty closed to new researchers, no security.txt (15). 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. ## 6. Transparency & trust, 63 out of 100, up to 3.2 more on the total Made of editorial 51, provenance 75. Why it scored 63: Closed service with published terms, which the preview disclaimer limits by excluding service levels, support and indemnities (15). The help article says the server stores no mural content, keeps OAuth tokens, registration records and session state in Redis, and that customer content isn't used for training. It also says token keys have no TTL and that revocation and retention still need a documented policy, and the privacy statement's body didn't render for us (18). No deprecation policy. The preview may change or end at any time without notice (0). A public subprocessor list with locations, mostly the US, and US hosting on Microsoft Azure by default with workspace-level data residency on Enterprise (18). 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): - Domain age: mural.co, no registry record we could read (0 of 15) - security.txt: not found (0 of 10) ## 7. Maintenance & community, 75 out of 100, up to 2.2 more on the total Why it scored 75: Registry version 1.0.0 published on 5 October 2026 and an MCP update in the 29 September release notes (30). Three dated MCP entries in 90 days, the public preview and fixes on 8 September, read and write changes on 29 September and the registry release on 5 October (20). Weekly public release notes, support@mural.co routing to a technical specialist and a community site, not tested (10). In the official MCP registry as co.mural/mural under Mural's own domain (15). Closed hosted service with no package or CI to assess (0). 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. - unchecked: the MCP tools/list, tool count, input schemas and readOnlyHint or destructiveHint annotations, which need an OAuth sign-in with a paid Mural account - Whether the Mural REST API's rate limits apply to MCP calls - unchecked: the privacy statement and DPA retention terms (the page body didn't render for us) - Price, if any, once MCP leaves public preview - The www.mural.co/ai/mcp page says both 'Coming soon' and 'currently available through Public Preview', and its two buttons point to sales and signup the wrong way round ## Weaknesses - Public preview, with Mural's service levels and support obligations excluded - The mural must stay open in a foreground browser tab, so it can't run headless - No published tool list, input schemas, rate limits or error responses - No export of images, PDF or diagram code through MCP - Needs a paid Mural plan, and Enterprise admins must switch it on ## 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. - Ask the person to open the target mural in a foreground browser tab, signed in to the connected account, before calling any tool - Work on one mural at a time and name it explicitly when switching - Request only murals:read when the task only reads a board - Deletes go through without a server-side prompt. Confirm with the person first, and suggest duplicating important murals - If a tool is missing or renamed, reconnect the connector to refresh the cached tool list ## What the review panel asked for - Publish the tool reference - Document error responses ## 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.