Mermaid Chart MCP by Mermaid Chart

# Fix list: Mermaid Chart MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/mermaid-chart, the October 2026 research run, assessed 1 October 2026. Grade F, 31.7 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 Mermaid Chart 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, 15 out of 100, up to 17 more on the total

Why it scored 15: No status page. The docs link none, and status.mermaidchart.com fails its TLS handshake (0). No readable incident history (5). No rate limits documented (0). No 429 or retry guidance (0). The terms promise "commercially reasonable efforts" and no SLA (0). The server is listed in the official registry as 1.0.0 and documented as a product, not a beta (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.

## 2. Security & auth, 20 out of 100, up to 14 more on the total

Why it scored 20: Render and validation tools need no credentials. Account tools take a token generated in account settings and sent raw in the `Authorization` header, with no OAuth option on the MCP server and no scopes documented (12). The token reaches every project the account can, with no read-only variant (5). Project diagrams and the GitHub, Jira and Notion helpers can bring other people's text into context, and we found no injection guidance (3). No audit log found (0). No security page, disclosure policy or certification found, and /.well-known/security.txt answered 401 on 30 September (0).

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.

## 3. Schema & documentation, 32 out of 100, up to 11.1 more on the total

Why it scored 32: Closed server. The 30 September check read typed tool inputs from an unauthenticated tools/list, which we couldn't repeat (15). mermaid.ai/llms.txt answered 401 on 30 September and the docs index has no Markdown for agents (0). The docs give one line for each of 9 tools, while the live server listed 25 on 30 September, including GitHub, Jira and Notion helpers with no docs (6). Input constraints unread (7). Setup examples, no documented errors (4). No changelog, and the registry entry hasn't changed since 18 September 2025 (0).

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. Agent ergonomics, 34 out of 100, up to 10.7 more on the total

Why it scored 34: 25 tools on the live server per the 30 September check, 9 of them documented (15). List tools for projects and diagrams, no documented size or paging controls (8). Errors undocumented (3). No annotations or retry guidance found, live annotations unchecked (0). Rendering needs only the Mermaid code, and there's one official SDK, in TypeScript (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.

## 5. Payments & pricing, 45 out of 100, up to 6.9 more on the total

Why it scored 45: No x402, MPP or L402 (0). Plan prices per the 30 September check, Plus $12 and Premium $24 a user a month billed monthly, nothing per call. The pricing page needs JavaScript and didn't render for us today (10). Rendering and validation are free with no account (20). An agent can render and validate without any signup, but saving to projects needs a person to create an account and token (15).

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.

## 6. Transparency & trust, 48 out of 100, up to 4.6 more on the total

Made of editorial 29, provenance 66.

Why it scored 48: The MCP server and editor are closed with published terms. Mermaid itself and the SDK are MIT (15). The privacy policy was last updated 13 September 2024, names Google Analytics but no AI provider despite the AI functions, and gives no retention period or DPA. The terms keep customer content for 20 days after the term ends (10). No deprecation notices found, and the move from mermaidchart.com to mermaid.ai came with redirects but no dated notice we could find (0). Processors are described by category only, no locations (4).

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: mermaid.ai, registered 2017-12-16 (8 years) (11 of 15)
- Status page: not found (0 of 10)
- Changelog: not found (0 of 10)
- security.txt: could not be fetched (0 of 10)

## 7. Maintenance & community, 53 out of 100, up to 4.1 more on the total

Why it scored 53: The official TypeScript SDK, @mermaidchart/sdk 0.2.8, was tagged on 17 September 2026 (30). Two SDK releases since 3 July (0.2.7 on 31 July and 0.2.8) and no dated server changes (0). No changelog, support by email, not tested (5). In the official MCP registry as com.mermaidchart/mermaid-mcp, but the entry dates from 18 September 2025 and still points at mcp.mermaidchart.com rather than mcp.mermaid.ai (12). The SDK repo runs lint and tests in CI (6).

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 live tools/list today (needs an MCP client); tool count and schemas are from the 30 September check
- unchecked: pricing page (JavaScript-only); prices are from the 30 September check
- unchecked: mermaid.ai/privacy-policy (refused for rate limits); read the /web/privacy-policy copy linked from the docs instead
- Whether the account token can be scoped or revoked, and which plan first issues one
- What the undocumented GitHub, Jira and Notion tools do and what data they reach

## Weaknesses

- Docs list 9 tools while the live server listed 25, including undocumented GitHub, Jira and Notion helpers
- Account tools take a raw token in the Authorization header, with no OAuth or scopes
- No status page, rate limits, changelog, security page or SLA
- Privacy policy last updated September 2024 and names no AI provider
- No public REST API reference, and API access is by application form

## 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.

- Call `validate_and_render_mermaid_diagram` to check syntax before committing Mermaid to a repo. It needs no token
- Only add the token if you need to save into Mermaid Chart projects. It reaches every project on the account
- If you only need a picture, the open-source mermaid-cli renders locally with no network call
- Use mcp.mermaid.ai. The registry still lists the older mcp.mermaidchart.com host

## What the review panel asked for

- Document all 25 tools
- MCP OAuth
- document all 25 tools
- publish 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.