draw.io + MCP by draw.io

# Fix list: draw.io + MCP

From Anchor Terminal's listing at https://www.anchorterminal.com/tools/drawio, the October 2026 research run, assessed 1 October 2026. Grade B, 62.4 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 draw.io + 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, 50 out of 100, up to 10 more on the total

Why it scored 50: Better Stack status page at status.draw.io with 30, 60 and 90-day bars for app.diagrams.net and the Atlassian apps, but mcp.draw.io isn't one of the monitored components (15). Every bar reads 100 per cent and no incident log is shown, so less than the full 30 (25). No rate limits published (0). No 429 or retry guidance (0). No SLA found (0). The hosted MCP App and @drawio/mcp 1.6.3 are released, not preview (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. Agent ergonomics, 49 out of 100, up to 8.3 more on the total

Why it scored 49: Two tools on the hosted App and seven on the npm server, but `create_diagram` appends the 34,555-byte XML reference and the 14,092-byte Mermaid reference to its description, roughly 13,000 tokens for one tool (10). `list_pages` and `get_page` read one page at a time, no other size controls found (10). Error responses aren't documented (5). Hosted tools are annotated readOnlyHint and idempotentHint. The npm server's seven tools carry no annotations (14). One required parameter per tool with stated defaults, no SDK (10).

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. Security & auth, 55 out of 100, up to 7.9 more on the total

Why it scored 55: No credentials anywhere, and the servers touch no user account or stored data, so there is nothing to scope or leak (20). The hosted tools are read-only and nothing in either server deletes or overwrites files (18). Output is the agent's own diagram plus shape results from draw.io's index and icon service (10). No per-call log for the operator (0). No security.txt (404). The privacy policy names security@draw.io. No bug bounty or certification found. npm releases use Trusted Publishing with provenance (7).

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. Payments & pricing, 60 out of 100, up to 5 more on the total

Why it scored 60: Free and Apache 2.0, nothing to buy for the MCP servers or the editor, so the self-hosted rule applies. No payment protocol (0). Nothing to price (20). Free with no account or card (20). Keyless, an agent can connect with 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. Schema & documentation, 82 out of 100, up to 2.9 more on the total

Why it scored 82: Both servers declare typed input schemas, JSON Schema in the npm tool server and zod in the hosted App (25). No llms.txt. The XML and Mermaid references ship as Markdown, but inside the tool descriptions rather than as a page for agents (5). Descriptions say when to use and when not to, for example `search_shapes` is "ONLY for diagrams that need industry-specific, branded, or pictorial icons" and the format choice between Mermaid and XML is spelled out (20). Enums on `dark`, `postLayout`, `direction` and `routing`, `content` required, `xml` and `mermaid` mutually exclusive (13). Long worked references with examples, no documented error responses (9). Semver npm releases and a ChangeLog for the core editor, but no changelog file in the MCP repo (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.

## 6. Transparency & trust, 74 out of 100, up to 2.3 more on the total

Made of editorial 58, provenance 90.

Why it scored 74: Apache 2.0 (30). The privacy policy is v2.1 from 30 August 2023 and says personal data isn't stored or transmitted outside the UK. The hosted MCP App sends the diagram to draw.io's server, and the repo shows it running on Cloudflare Workers and Durable Objects, neither of which the policy mentions (15). No deprecation policy found, though the core ChangeLog records changes (3). No subprocessor list. We found no telemetry in the MCP tool definitions (10).

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)

## 7. Maintenance & community, 86 out of 100, up to 1.2 more on the total

Why it scored 86: Core editor v31.7.0 tagged on 1 October 2026, and @drawio/mcp bumped to 1.6.3 on 30 September (30). At least 20 core tags between 15 July and 1 October (20). Commits land most days, with 15 on 30 September alone. The core repo doesn't take pull requests, and we didn't read issue replies (15). In the official MCP registry as io.draw/mcp under the draw.io domain namespace, though the entry is still at 1.0.3 from 3 August (15). Nine test files, run only in the manual publish workflow, not on every push (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.

- How quickly jgraph answers issues on drawio-mcp (issues aren't in git and we didn't read them)
- Whether the hosted MCP App has any rate limit
- Which region and provider the hosted MCP's Cloudflare deployment keeps diagram data in, given the UK-only statement in the privacy policy

## Weaknesses

- Tool descriptions embed a 34.5 KB XML reference and a 14 KB Mermaid reference, roughly 13,000 tokens
- No REST API to save, list or render diagrams
- PNG, SVG and PDF export need draw.io Desktop's CLI or a person in the editor
- No rate limits, SLA or security.txt, and mcp.draw.io isn't on the status page
- The npm tool server's seven tools carry no readOnlyHint or destructiveHint annotations

## 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.

- Pass `mermaid` to `create_diagram` for any type on its Mermaid list. Use `xml` only for icons, mockups or hand-placed layouts
- Call `search_shapes` before writing XML with cloud or network icons, so the style strings are exact
- Set `postLayout: "elk"` for flowcharts or `routing: "libavoid"` for hand-placed diagrams, never both
- Use the npm server or the plugin when the diagram mustn't leave the machine. The hosted App sends it to draw.io's server
- Expect the tool list to cost about 13,000 tokens before the first call

## What the review panel asked for

- Hosted PNG export
- Slimmer create_diagram description
- references as resources
- 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.