Structurizr + MCP by Structurizr

# Fix list: Structurizr + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/structurizr, the October 2026 research run, assessed 1 October 2026. Grade C, 60.2 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 Structurizr + 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. Security & auth, 43 out of 100, up to 10 more on the total

Why it scored 43: A per-workspace API key in the `X-Authorization` header, an admin key for listing, and a regenerate endpoint added in May 2026. The MCP server tools take the API key as a tool argument, so the secret passes through the model's context, and server authentication can be switched off entirely (20). Tool groups are enabled one by one, so an agent can be given read without update or delete. There is no read-only key (12). The hosted tools return parse results of the agent's own DSL. Workspaces fetched from a server can hold text written by others (9). No audit log found (0). No security.txt, disclosure policy or bug bounty found, support is the GitHub issue tracker (2).

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.

## 2. Agent ergonomics, 55 out of 100, up to 7.3 more on the total

Why it scored 55: Six compact tools on the hosted MCP, and the self-hosted image enables tool groups by flag (`-dsl`, `-server-read`, `-server-update` and so on) (25). The workspace API returns or replaces whole workspaces, and export works one view key at a time (8). Errors come back as exception text, and API errors aren't documented (8). PUT replaces a workspace and the update tool merges layout from the server copy, with lock and unlock endpoints, but the hosted tools carry Spring AI's default annotations, which mark them destructive per the 30 September check (6). Official Java client library, no second language (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. Schema & documentation, 61 out of 100, up to 6.3 more on the total

Why it scored 61: OpenAPI 3.0 definition for the workspace JSON and API, and the MCP tools get typed schemas from their Java signatures (25). No llms.txt found (0). Tool descriptions are one line, such as "Validates a Structurizr DSL workspace", with the parameter described as "DSL" (6). Required flags and a numeric workspace ID, no enums (8). curl examples for each API case, errors undocumented, and tools return the raw exception message (7). Dated changelogs for the application and the library (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.

## 4. Payments & pricing, 50 out of 100, up to 6.3 more on the total

Why it scored 50: Apache 2.0 code with a paid option, the licence for prebuilt binaries. No payment protocol (0). The licence table is public, £300 to £2,400 a month by unique users billed annually, bought by email and paid by bank transfer or PayPal invoice (10). Building from source is free, and a 14-day trial licence comes from trial.structurizr.com with no payment (20). The hosted MCP needs no key and the local tools need no signup (20).

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. Reliability, 73 out of 100, up to 5.4 more on the total

Why it scored 73: The hosted cloud API shut down on 30 September 2026, so what an agent calls now is a server you run plus a small hosted MCP, and we used the self-hosted checklist. Prebuilt binaries and Docker images with Java 21 stated (20). A Maven workflow builds and runs the unit tests on every push to main, integration tests excluded, pass state not checked (18). The changelog fixes reported issues #106 to #130 within weeks, open issues not read (15). Date-stamped application releases and a semver library (v6.2.3), each with a changelog (12). The server is a stable product, but the MCP module's README calls it "an experimental MCP server" and mcp.structurizr.com has no status page or published limits (8).

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.

## 6. Maintenance & community, 68 out of 100, up to 2.8 more on the total

Why it scored 68: Application release 2026.09.19 on 19 September 2026, 12 days ago (30). Two releases since 3 July (2026.09.19 and library v6.2.3), short of three (0). Issues are referenced and fixed in the changelog, but all 200 commits since February are by one person (15). Not in the official MCP registry, and the official Java library is current at v6.2.3 (15). CI on every push and Docker base images bumped on 19 September (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.

## 7. Transparency & trust, 80 out of 100, up to 1.8 more on the total

Made of editorial 80, provenance 80.

Why it scored 80: Apache 2.0, and the prebuilt binaries add a EULA (28). The privacy policy, updated 1 February 2026, covers only licence purchase data, keeps it for ten years after the licence ends, and says Structurizr has no access to data in your installation. The hosted MCP isn't covered (20). The end-of-life page and cloud migration guide gave dated notice, sign-ups closed 31 December 2025 and shutdown on 30 September 2026 (20). No telemetry mentioned in the docs or EULA, not verified in code (12).

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):

- Status page: not found (0 of 10)
- 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.

- unchecked: docs.structurizr.com pages directly (our fetches were refused for rate limits); content read from the docs site's GitHub source instead
- Whether the default branch CI is passing
- Whether the prebuilt binaries or the hosted MCP send any telemetry
- Open issue count and response times on GitHub

## Weaknesses

- The hosted cloud API is gone. Storage and rendering need your own server
- Prebuilt server binaries need a paid licence counted per unique user, including API clients
- The MCP module is labelled experimental, with one-line tool descriptions
- Self-hosted MCP server tools take the workspace API key as a tool argument
- No security.txt or disclosure policy, and one maintainer wrote every commit since February

## 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 then `inspect` on the DSL before pushing a workspace
- Use the Mermaid export when the diagram has to render in Markdown without a Structurizr server
- Export needs a view key. Parse the DSL first to list the views
- Run the `structurizr/mcp` image with only the flags you need, such as `-dsl -server-read`, to keep write and delete tools out of reach
- The workspace API returns JSON, never images. PNG and SVG come from the separate export command

## What the review panel asked for

- Key from environment
- Images from the API
- richer tool descriptions
- accurate read-only hints

## 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.