MCP (Model Context Protocol) capabilities with Payload
- capability exposure inferred + 4
- tool safety inferred + 5
- trust mitigators mixed − 8
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 · 1
- B · 23 → B · 16
- C · 35 → B · 23
No known CVEs for this server.
- medium dangerous code
dynamic exec: new Function()
analyzed v3.90.1 · analyzer v33 · 9h ago
danger signals2
- dynamic code execution new Function() package/dist/utils/schemaConversion/convertCollectionSchemaToZod.js :31
return new Function('z', `return ${transpileResult.outputText}`)(z); - dynamic code execution new Function() package/src/utils/schemaConversion/convertCollectionSchemaToZod.ts :39
return new Function('z', `return ${transpileResult.outputText}`)(z)
[](https://mcpobservatory.com/servers/npm:@payloadcms/plugin-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 alessiogr.