Serve multiple stdio MCP servers from one container: path routing, hub meta-tools, OAuth 2.1 + API tokens for ChatGPT, Claude, Cursor and other MCP clients
- capability exposure inferred + 28
- trust mitigators mixed − 11
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 6d ago · see ecosystem CVEs →
- B · 25 → B · 17
No known CVEs for this server.
No tool-safety findings — heuristic detectors run on the compute-risk cadence; a finding appears when a tool trips a rule.
analyzed commit 3fdbdb7 · analyzer v33 · 1w ago
danger signals2
- suspicious endpoint 169.254.169.254 (cloud metadata) ni-c-mcp-hub-3fdbdb7/test/cimd.test.ts :383
res.writeHead(302, { location: 'http://169.254.169.254/latest/meta-data/' }); - suspicious endpoint 93.184.216.34 ni-c-mcp-hub-3fdbdb7/test/cimd.test.ts :489
const clientId = 'https://93.184.216.34/oauth/client.json';
[](https://mcpobservatory.com/servers/github:ni-c/mcp-hub/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 ni-c.