Official draw.io MCP server for LLMs - Open diagrams in draw.io editor
- capability exposure inferred + 22
- tool safety inferred + 5
- supply-chain attested + 6
- trust mitigators mixed − 8
attested inferred mixed
The A–E grade is our heuristic synthesis — a "review this" prompt, not a verdict. Each factor is tagged by what backs it: attested (a verifiable record), reported (a third party's claim), or inferred (our own heuristic, e.g. permissions). See methodology.
grade last moved 1w ago · see ecosystem CVEs →
- B · 17 → B · 25
- B · 25 → B · 17
- C · 40 → B · 25
- C · 52 → C · 40
- C · 57 → C · 52
- B · 34 → C · 57
- B · 28 → B · 34
No known CVEs for this server.
- medium dangerous code
dynamic exec: indirect eval
- low dangerous code
env-secret-flows-to-network-js: A process environment value reaches a network call. Review whether it is a credential leaving the process; the ordinary API-wrapper shape (read a ke
analyzed v1.6.0 · analyzer v33 · 8h ago
danger signals2
- dynamic code execution indirect eval package/src/elk-engine.js :43
(0, eval)(src); - dynamic code execution indirect eval package/src/libavoid-pass.js :49
(0, eval)(src);
- supply-chain +6 supply-chain hub →
[](https://mcpobservatory.com/servers/npm:@drawio/mcp/security) Heuristic, inferred signals — false positives (legitimately powerful tools, forks, language ports) are expected. Treat each as "review this", not a verdict. See the ecosystem-wide picture on the security hub, or the fleet security of drawio.