A collection of MCP test servers including working servers (ping, resource, combined, env-echo) and test failure cases (broken-tool, crash-on-startup)
- capability exposureinferred+35
- inherited (deps)attested+15
- tool safetyinferred+12
- trust mitigatorsmixed−5
attestedinferredmixed
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 16m ago · see ecosystem CVEs →
No known CVEs for this server.
inherited (deps) · grade factor +15
- highdangerous code
credential logged in 1 file(s)
analyzed v1.1.72 · analyzer v18 · 10h ago
skills & prompt files 2
- agent-rulespackage/.cursor/rules/create-server.mdc
- agent-rulespackage/.cursor/rules/server-authoring.mdc
danger signals1
- credential in logscredential in logpackage/src/oauth-token-refresh-server.js:231
console.error(`✅ Token refreshed: new access token expires in ${ACCESS_TOKEN_EXPIRY_SECONDS}s`);
[](https://mcpobservatory.com/servers/npm:@msfeldstein/mcp-test-servers/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 msfeldstein.