Preview release of FusionAuth API MCP server
B low
- capability exposureinferred+10
- recent driftinferred+12
- tool safetyinferred+5
- trust mitigatorsmixed−8
inferredmixed
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 5m ago · see ecosystem CVEs →
- B · 26 → B · 19
- C · 38 → B · 26
Inferred surface — each links to servers holding it:
No known CVEs for this server.
- mediumdangerous code
dynamic exec: eval()
prompt-surface
shipped agent-instruction files + hidden-content / dangerous-code findings —
quoted from the analyzed source
analyzed commit bbacc53 · analyzer v20 · 20h ago
danger signals2
- dynamic code executioneval()FusionAuth-fusionauth-mcp-api-bbacc53/packages/mcp-api/src/index.ts:3838
const zodSchema = eval(zodSchemaString); - dynamic code executioneval()FusionAuth-fusionauth-mcp-api-bbacc53/packages/openapi-mcp-generator/src/generator/server-code.ts:238
const zodSchema = eval(zodSchemaString);
- recent drift+12 capability drift →
[](https://mcpobservatory.com/servers/github:FusionAuth/fusionauth-mcp-api/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 FusionAuth.