Model Context Protocol implementation for TypeScript - Client package
- capability exposure inferred + 18
- recent drift inferred + 20
- tool safety inferred + 5
- trust mitigators mixed − 9
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.
graded 10m ago · see ecosystem CVEs →
- C · 41 → B · 34
- B · 33 → C · 41
- C · 50 → B · 33
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed v2.0.0 · analyzer v28 · 3d ago
danger signals2
- dynamic code execution new Function() package/dist/ajvProvider-1b6pVpkg.cjs :2594
const validate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode)(this, this.scope.get()); - dynamic code execution new Function() package/dist/ajvProvider-97rDpkRx.mjs :2594
const validate = new Function(`${names_1.default.self}`, `${names_1.default.scope}`, sourceCode)(this, this.scope.get());
- recent drift +20 capability drift →
[](https://mcpobservatory.com/servers/npm:@modelcontextprotocol/client/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 ashwin-ant.