multi-provider-schema-output-agent
Server Details
Multi-Provider Schema Output Agent
- Status
- Healthy
- Uptime
- 100.0% over the last 24 hours
- Last Tested
- Transport
- Streamable HTTP · MCP 2025-11-25
- URL
- ChatGPT
- –
- Claude
- –
TDQS
Scored across 2 tools
invoke performs the actual task while selftest runs a fixed canned input for audit/verification purposes, so the two roles are distinguishable. There is mild overlap in that selftest is effectively a constrained call of invoke, which could tempt an agent to use it as a general free path, but the descriptions clearly mark it as evidence-only.
Both names are single lowercase imperative tokens, but 'selftest' is an unseparated compound noun/verb while 'invoke' is a bare verb, so there is no predictable verb_noun pattern to extrapolate from. With only two tools this is readable, but the convention is not clearly established.
A two-tool surface is thin even for a narrowly scoped schema-output agent; invoke plus selftest covers submission and verification but leaves little room for discovery or auxiliary operations. It is defensible for the agent's single purpose, but sits at the borderline under-scoped end.
The core lifecycle — turn prompt + schema into validated typed JSON — is fully covered by invoke, and selftest adds an audit/proof path that most servers lack. Gaps are minor: no batch invocation, standalone schema-validation endpoint, model/version discovery, or explicit error/retry contract.
Available Tools
2 toolsinvokeBInspect
Turn a prompt + a field schema into validated, typed JSON (Instructor over Gemini 2.5 Flash on Vertex AI).
Inputs: input (required).
selftestAInspect
FREE, no payment required. Runs this agent's real capability on a fixed canned input and returns the genuine result, an honest assertion grade, and the full trust manifest (signed Agent Card, JWKS, governance/licence chain, safety posture) with a proof link for every claim. Intended for registries, graders and auditors: this is behavioural evidence, not a self-description.
Inputs: no named parameters.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
Related MCP Connectors
Claude Schema Output Agent
Structured Output Agent (Openai)
Structured Output MCP Agent (Cryptography)
Structured Output MCP Agent (Instructor)
Related MCP Servers
- -
- FlicenseNot gradedqualityCmaintenanceIntegration Infrastructure Agents Actually Control39-
- AlicenseAqualityCmaintenanceTamper-Evident Autonomous Agent Action Audit & Governance Logging MCP Server27 npmMIT
- AlicenseBqualityAmaintenanceAIWorkHub turns any repo into a local AI coding factory: an AI manager follows your roadmap and drives Claude Code, Codex, OpenCode and Copilot as workers, with dependency-aware tasks and semantic review. Or use it standalone: a 34-language source graph with 37 query types, AI memory, session manager and knowledge base over MCP. Fully local, MIT.11612MIT
Glama MCP Gateway
Add one secure layer between your agents and this server.