# Fix list: Whimsical MCP From Anchor Terminal's listing at https://www.anchorterminal.com/tools/whimsical, the October 2026 research run, assessed 1 October 2026. Grade D, 52.7 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 Whimsical 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, 25 out of 100, up to 9.4 more on the total Why it scored 25: No x402, MPP or L402 (0). Plan prices are public per the 30 September check, Pro $10 and Business $20 per editor a month billed yearly, nothing per call (10). A $0 Free plan on which every MCP tool works, capped at 50 board objects a month. The pricing page needs JavaScript, so we couldn't confirm it takes no card (15). OAuth sign-in needs 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. ## 2. Agent ergonomics, 46 out of 100, up to 8.8 more on the total Why it scored 46: 17 tools in the published tool spec, with syntax docs loaded on demand through `how_to` (18). `search`, `file_tree` and `fetch` scope what comes back, and `fetch` can return a PNG snapshot (10). Error responses aren't documented (5). Read and write tools are split in the docs, and we couldn't read the readOnlyHint or destructiveHint annotations on the live server (5). `generate_diagram` and `generate_mind_map` lay out automatically, no SDK (8). 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, 60 out of 100, up to 8 more on the total Why it scored 60: Status page at status.whimsical.com, run on Sorry, with a history page (20). The last incident was on 6 March 2026, so the last 90 days are clean (30). Rate limits aren't documented (0). No 429 or retry guidance (0). No SLA found (0). The remote MCP server is generally available, version 1.1.0 in the official registry (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. Schema & documentation, 54 out of 100, up to 7.5 more on the total Why it scored 54: The server is closed, so we couldn't read the tool schemas. MCP requires typed inputs, and the tool spec page documents each tool (15). No llms.txt. The `how_to` tool hands the agent Whimsical's syntax docs on demand (5). The tool spec gives each tool's purpose and splits them into 6 read and 11 write tools, without when-not-to-use guidance (12). Input constraints unread (7). No documented error responses (5). Registry versions 1.0.0 (13 August) and 1.1.0 (8 September), and a changelog page that needs JavaScript (10). 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. ## 5. Security & auth, 58 out of 100, up to 7.4 more on the total Why it scored 58: OAuth 2.1 with PKCE and separate read and write scopes per the 30 September check, no API keys (28). A read scope exists, but `delete` removes files or objects with no confirmation step documented (12). `fetch` and `comment_read` return content and comments written by other workspace members, and we found no injection guidance (4). No audit log for MCP calls found (0). SOC 2 Type II, a vulnerability disclosure policy and no bug bounty. No security.txt per the 30 September check (14). 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. Maintenance & community, 56 out of 100, up to 3.9 more on the total Why it scored 56: Registry version 1.1.0 published on 8 September 2026, 23 days ago (30). Two dated releases since 3 July (1.0.0 on 13 August, 1.1.0 on 8 September), and the changelog page didn't render for us (0). Support by email, not tested (8). In the official MCP registry as com.whimsical/mcp under Whimsical's own domain (15). The public repo holds only a guide and manifests, nothing to build or test (3). 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, 72 out of 100, up to 2.5 more on the total Made of editorial 53, provenance 90. Why it scored 72: The server is closed with published terms. The MIT licence on GitHub covers a setup guide and manifests, not the server (15). Privacy policy from August 2025 with a DPA, US hosting with Standard Contractual Clauses for transfers, AI supplementary terms, and no retention periods in days (22). No deprecation policy or dated notices, and the REST API is still a closed beta (0). A separate subprocessor list, and hosting in the US named (16). 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) ## 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. - Exact tool count. The published tool spec lists 17 remote tools, while the 30 September check counted 18 on the live server - unchecked: the changelog and pricing pages (JavaScript-only); prices are from the 30 September check - unchecked: tool annotations and input schemas on the live server - Whether any plan carries an SLA ## Weaknesses - No API keys, so it can't run headless or in CI - Rate limits and error responses aren't documented - REST API is a closed, read-only beta - Free plan caps creation at 50 board objects a month - Export is PNG snapshots only. No SVG, draw.io or diagram code out ## 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. - Use `generate_diagram` or `generate_mind_map` for laid-out output rather than placing shapes with `create` and `edit` - Call `how_to` for Whimsical's syntax before writing a large diagram - Use `fetch` when you need a PNG snapshot of a board - `delete` removes files or objects without asking. Confirm with the person first ## What the review panel asked for - API keys for CI - SVG or code export - publish tool schemas - 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.