Works with the AI tools you already use
MCP Client Evidence Gate
by Corey Jacobs
Automated compatibility testing and evidence generation for MCP servers against Codex and Qwen clients.
Free
Free forever. No account required to browse.
See it in action
You say
Check if my local MCP server at ./build/index.js exposes all tools correctly to Codex CLI and generate a report.
Your agent does
I ran the discovery gate for your local MCP server. Results:
- Codex CLI 0.142.2: PASS (6 tools discovered)
- Qwen Code 0.19.2: PASS (6 tools discovered)
Full evidence report saved to report.md and receipt.json. No schema errors detected.
About this skill
MCP Client Evidence Gate is a living compatibility/evidence skill for MCP builders who need to keep client verification claims current as MCP clients, agent tools, and marketplace expectations change.
Use it when you need to verify MCP server discovery behavior before publishing, compare discovery results between clients, or generate structured compatibility receipts that separate actual-client evidence from fixture coverage and NOT_EXECUTED paths.
This is subscription-priced because MCP compatibility evidence goes stale. Codex changes. Qwen changes. Client discovery behavior changes. Marketplace expectations change. A one-time static checklist is not enough when the thing being verified keeps moving.
This skill helps you:
- Validate MCP server discovery before publishing a release.
- Compare discovery behavior between supported clients.
- Generate local evidence receipts for MCP compatibility claims.
- Separate actual-client evidence from fixture/direct-protocol checks.
- Prevent documentation overclaims before buyers or users hit a failure.
- Keep a repeatable verification gate as MCP client behavior evolves.
Verified v0.1 scope:
- Codex CLI v0.142.2 stdio discovery evidence.
- Qwen Code v0.19.2 stdio discovery evidence.
- Fixture/direct-protocol checks.
- Explicit NOT_EXECUTED boundaries for untested paths.
This is not a universal MCP conformance suite. It does not claim full protocol coverage, OAuth coverage, hidden client behavior, Streamable HTTP actual-client verification, safe-call actual-client verification, or compatibility with untested clients.
Best for MCP server authors, agent builders, tool developers, and marketplace sellers who need living compatibility evidence instead of static claims.
More provider updates incoming.
How to install
Drop the file into your AI Agent. Works with Claude, Cursor, ChatGPT, and 20+ more.
Reviews
No reviews yet
Be one of the first to try it. Every listed skill passes our trust checks below.
Security scanned
Passed our 8-point scan before listing
Fresh listing
Recently published to Agensi
Free forever
No account required to browse
Trust & safety
Security scanned
Verified clean 22 days ago
- Free forever, no account required
Frequently Asked Questions
Popular in AI Agents & LLM Ops
designing-hybrid-context-layers
Architects the right retrieval strategy for every query — teaching your agent when to use RAG, a knowledge graph, or a temporal index instead of defaulting to vector search for everything.
AI Coding Prompt Refiner for Better Developer Results
Transforms vague coding requests into precise, scoped, testable, AI-ready prompts for Cursor, Claude Code, Codex CLI, Replit, and other coding agents.
skill-creator
The "Skill for building Skills": Automate creating, testing, and optimisation of custom workflows.
instruction-layer-auditor
Audit and de-conflict complex agent instruction stacks to fix inconsistent behavior and logic bloat.