MCP server for verifying Creduent agent identities and querying the Creduent Registry for attestation status
Single tool with adequate schema but weak descriptions and no error guidance. verify_agent has a clear name and proper input schema (target: string), but the description (95 chars) lacks WHEN to use it, prerequisites, or what the return fields mean. No parameter description for 'target' beyond the tool description. Output schema is undocumented, LLMs cannot plan downstream calls without knowing the structure of response_obj fields (agent_id, self_verified, attestation_level, etc.). No error handling guidance; exceptions are caught silently and degrade gracefully, but the LLM receives no actionable recovery hints. Naming is good (verb_noun pattern), but overall definition quality is below production baseline.
Verify the identity of a Creduent agent using their domain or agent:// URI, and query the Creduent Registry for attestation status.
Output schema undocumented. response_obj fields (agent_id, self_verified, creduent_attested, attestation_level, public_key, endpoint, capabilities, checked_at, etc.) are not described. LLMs cannot infer field types or plan downstream tool calls.
Parameter 'target' lacks a description. Tool description mentions 'agent:// URI' and 'domain' formats, but the parameter itself has no dedicated description explaining format, constraints, or examples.
Tool description (95 chars) is too brief. Does not explain WHEN to use verify_agent vs other identity verification tools, what prerequisites exist (e.g., network access to Creduent registry), or what each response field means.
No error handling guidance. Exceptions are caught and silently degrade (e.g., 'registry_offline' state), but LLMs receive no actionable recovery hints. Should return structured errors with retry guidance.
| Scored | Grade | Overall | Spec posture | Rubric |
|---|---|---|---|---|
| 2026-09-23 | F | 49 | 2026-07-28+ | v2 |
STDIO transport only. Server is not remotely accessible and cannot be used by hosted MCP clients. Limits deployment and integration scenarios.