Diagrams.so API + MCP by Diagrams.so (RedHold LLC)

# Fix list: Diagrams.so API + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/diagrams-so, the October 2026 research run, assessed 1 October 2026. Grade C, 60.1 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 Diagrams.so 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. Reliability, 30 out of 100, up to 14 more on the total

Why it scored 30: No status page yet. The status and SLA page says the link "is added to the navbar once the status page is live" (0). No readable incident history (5). The rate-limit guide names per-key and per-IP limits, says test keys get less, and publishes no numbers (0). 429 carries RATE_LIMIT_EXCEEDED, the guide says to honour Retry-After and back off exponentially, and billable writes take an Idempotency-Key (15). The terms say "we offer no service-level commitment" (0). /api/v2 launched in July 2026 as a public API, 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. Payments & pricing, 32 out of 100, up to 8.5 more on the total

Why it scored 32: No x402, MPP or L402 (0). Plan prices and the credit price ($5 per 25 credits) are public, but the developer docs say per-action costs "are shown in the app". The SDK changelog gives a 0.5 to 3.0 credit range for generate, edit, fix and re-layout (12). Free plan with 10 one-time credits, marked "No Card Required" (20). The device login still needs a person to approve an emailed code in the 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.

## 3. Security & auth, 67 out of 100, up to 5.8 more on the total

Why it scored 67: Bearer API keys with live and test prefixes, described as scoped with instant revocation, a 25-active-key cap, or a device-flow login whose one-time code is emailed, never put in a URL. Which scopes exist isn't documented (28). Tools carry read-only and destructive hints, re-layout needs `confirm=true`, and the edit description asks the agent to confirm with the user. No read-only key type found (14). `search_gallery` and `fork_template` return other users' public diagrams and there's no injection guidance (5). Every charge is itemised through `GET /usage/history` and responses carry a request ID (10). security.txt valid per the 30 September check, a vulnerability disclosure policy with safe harbour and a 3-business-day acknowledgement. No bug bounty or SOC 2 (10).

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.

## 4. Maintenance & community, 71 out of 100, up to 2.5 more on the total

Why it scored 71: MCP server v1.4.6 tagged on 19 August 2026, 43 days ago (20). Eight MCP tags and three SDK tags between 3 and 19 August (20). Both repositories are young with almost no outside issues, and neither has had a commit since 19 August (8). Listed in the official MCP registry as io.github.RedHold/diagrams-so-mcp, latest 1.4.6 published 19 August 2026, under the GitHub-verified namespace (15). CI builds on Node 18, 20 and 22 and tests the SDKs on Python 3.9 and 3.12. Two runtime dependencies (8).

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.

## 5. Schema & documentation, 85 out of 100, up to 2.4 more on the total

Why it scored 85: OpenAPI 3.1 at api.diagrams.so with 32 operations, and every one of the 23 MCP tools has a typed zod input schema (25). llms.txt (10). MCP descriptions say what each tool does, whether it costs credits and, for edit, to confirm with the user first, and the server instructions give the call order (16). Inputs have required fields and minimum lengths, but `cloud_provider` and `diagram_type` are free strings with the options listed in the description, not enums (10). An errors guide documents the envelope, codes and what to retry, while the OpenAPI file only lists 422 per operation (11). Versioned path, a public changelog dated by month and a versioning guide (13).

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. Agent ergonomics, 85 out of 100, up to 2.4 more on the total

Why it scored 85: 23 MCP tools in one 35 KB source file, no toolsets or read-only subset, and every billable tool returns the full draw.io XML (15). Cursor pagination on list endpoints (15). Errors return a code, HTTP status and request ID, and an ambiguous billable failure tells the agent to check `get_usage_history` before retrying (20). Idempotency-Key on billable calls, which the SDKs attach automatically, and readOnlyHint or destructiveHint on all 23 tools (20). Only `prompt` is required to generate, official Python and TypeScript SDKs (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.

## 7. Transparency & trust, 75 out of 100, up to 2.2 more on the total

Made of editorial 75, provenance 75.

Why it scored 75: MCP server and SDKs are Apache 2.0, the service is closed with clear terms (20). Privacy policy dated 15 September 2026. Diagrams kept until deleted, inputs not used for training, a DPA for business customers, but no retention periods in days (22). The terms promise at least 90 days' notice before a major API version is retired and 30 days for material changes to the terms (18). Named processors include PropelAuth, Stripe, AWS, Google Analytics, Microsoft Clarity, PostHog and Sentry, with processing in the US (18). The MCP README says the server "contains no telemetry", yet since August 2026 it tags each request with the tool name in an `X-Diagrams-Tool` header to the vendor's own API, which the README and SECURITY.md don't mention (-3).

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: diagrams.so, registered 2026-02-05 (under a year) (0 of 15)
- Status page: not found (0 of 10)

## Deductions

Each comes off the total. A fixed and documented problem counts for less at the next check.

- Early August 2026. The API moved its device login to an emailed code without notice, which broke the MCP server's in-chat connect path and sent one rejected request per tool call until v1.4.6 fixed it on 19 August. Fixed and documented in the server's changelog, so the deduction is reduced (https://github.com/RedHold/diagrams-mcp-app-core/blob/main/CHANGELOG.md).

## 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.

- Independent confirmation of RedHold LLC in the Virginia SCC register (OpenCorporates rate-limited us and Bizapedia is blocked by robots.txt)
- Which scopes an API key can carry
- Rate-limit numbers for live and test keys

## Weaknesses

- No status page or SLA, and the terms disclaim any service-level commitment
- Rate limits exist per key and per IP but no numbers are published
- Per-action credit costs are shown only in the app
- Domain registered in February 2026, and no commits to either repo since 19 August 2026
- Login is a device flow a person must approve by email, so there's no autonomous signup

## 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.

- Send an Idempotency-Key on generate, edit, fix and re-layout. If a billable call times out, check `get_usage_history` before retrying
- Generation is synchronous and can run for minutes. The SDKs default to a 450 s timeout, or use `POST /diagrams/stream`
- Call `list_capabilities` first. `cloud_provider` and `diagram_type` are free strings, and a wrong value fails the call
- `relayout_diagram` refuses to run without `confirm=true`, because every re-layout is billed
- Test keys (dgz_test_) spend the same credits as live keys

## What the review panel asked for

- A status page
- Enums on inputs
- enums for provider and type
- slimmer billable 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.