traced-claude-format-guard
Server Details
Traced Claude Format Guard
- 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 proxied LLM completion while selftest runs a fixed canned capability check and returns a trust manifest; the purposes are largely distinct. There is mild overlap since both ultimately exercise the model and return evidence, but an agent can pick correctly.
Both names are single lowercase verb-style tokens with no style mixing, so the set reads consistently. However, neither follows a verb_noun pattern, so the naming gives little hint about what is being acted on.
Only two tools, which is thin even for a narrow traced-proxy server. The scope is legitimately small, but the surface feels minimal rather than deliberately scoped.
For its stated purpose (traced LLM completions plus verifiable behavioural evidence) the surface covers the core lifecycle: call and prove. Minor gaps exist around configuration, model selection, or error/health inspection, which agents cannot work around without other tooling.
Available Tools
2 toolsinvokeBInspect
Proxy Gemini (Vertex AI) completions wrapped in OpenTelemetry trace spans; returns the answer plus the trace/span id.
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 MCP Traced Agent
Traced Structured Output Agent (Groq)
Related MCP Servers
- AlicenseNot gradedqualityCmaintenanceLocal Cost Guard and runtime guardrails for AI agents in Claude Code.124 npmMIT
- FlicenseNot gradedqualityDmaintenanceAutomatically detects and obfuscates sensitive data (PII, secrets, etc.) before Claude processes it, with lossless restoration for client deliverables.6-
- AlicenseNot gradedqualityCmaintenanceActs as an in-line protective proxy for Claude and MCP clients, enabling secret redaction, SSRF and path-traversal blocking, destructive-command prevention, prompt-injection scanning, and tamper-evident audit logging with sub-millisecond overhead.MIT
- FlicenseNot gradedqualityFmaintenanceEnables Claude to work on documents containing personal data by pseudonymizing names, addresses, IBANs, health data and other GDPR categories locally before they are sent, then restoring the real values on your own machine. Supports Word, Excel, PowerPoint, PDF, CSV, Markdown, e-mail and other formats with consistent pseudonyms per project and no data leaving the computer.-
Glama MCP Gateway
Add one secure layer between your agents and this server.