Model Context Protocol implementation for TypeScript
- tool safety inferred + 12
- trust mitigators mixed − 14
These factors total -2, not 0: the score is bounded to 0–100 after they are summed, so this one is floored at 0. The factors are left as they were applied rather than rewritten to make the column add up.
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 · 16 → A · 0
- C · 43 → B · 16
- B · 31 → C · 43
- B · 34 → B · 31
- C · 46 → B · 34
- C · 54 → C · 46
- C · 51 → C · 54
- C · 42 → C · 51
- C · 51 → C · 42
- D · 68 → C · 51
No known CVEs for this server.
- high dangerous code
credential logged in 2 file(s)
analyzed v1.30.0 · analyzer v33 · 4w ago
danger signals2
- credential in logs credential in log package/dist/cjs/examples/server/elicitationUrlExample.js :325
console.log(`🔑 Received API key \x1b[32m${apiKey}\x1b[0m for session ${sessionId}`); - credential in logs credential in log package/dist/esm/examples/server/elicitationUrlExample.js :320
console.log(`🔑 Received API key \x1b[32m${apiKey}\x1b[0m for session ${sessionId}`);
[](https://mcpobservatory.com/servers/npm:@modelcontextprotocol/sdk/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 fweinberger.