MCP Client Evidence Gate
by Corey Jacobs
Automated compatibility testing and evidence generation for MCP servers against Codex and Qwen clients.
- Validate MCP server compatibility before publishing a release.
- Compare tool discovery results between two server revisions.
- Generate structured compatibility receipts for client verification.
$7
/moSubscription · cancel anytime
Secure checkout via Stripe
- Always the latest version
- Delivered live to your agent via MCP
- Cancel anytime, access ends at period end
Included in download
- Downloadable skill package
- 3 permissions declared
AI Autodidact living at the edge.
Media gallery
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.
MCP Client Evidence Gate
by Corey Jacobs
Automated compatibility testing and evidence generation for MCP servers against Codex and Qwen clients.
$7
/moSubscription · cancel anytime
Secure checkout via Stripe
- Always the latest version
- Delivered live to your agent via MCP
- Cancel anytime, access ends at period end
Included in download
- Downloadable skill package
- 3 permissions declared
- Instant install
Media gallery
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.
Use Cases
- Validate MCP server compatibility before publishing a release.
- Compare tool discovery results between two server revisions.
- Generate structured compatibility receipts for client verification.
- Verify stdio transport initialization across multiple AI client binaries.
- Catch MCP documentation overclaims before listing or release.
- Confirm Codex CLI can discover an MCP server before publishing.
- Confirm Qwen Code can discover an MCP server before publishing.
- Separate actual-client evidence from fixture-only test coverage.
- Record NOT_EXECUTED paths for untested MCP clients or transports.
- Run an MCP release gate before marketplace submission.
Known Limitations
Limited to verified v0.1 evidence: Codex CLI v0.142.2 and Qwen Code v0.19.2 stdio discovery, plus fixture/direct-protocol checks. Does not claim universal MCP conformance, OAuth coverage, Streamable HTTP actual-client verification, safe-call actual-client verification, hidden client behavior, or untested client compatibility. Untested paths are marked NOT_EXECUTED.
How to Install
mkdir -p ~/.claude/skills && curl -sL https://www.agensi.io/api/install/mcp-client-evidence-gate -o /tmp/mcp-client-evidence-gate.zip && unzip -o /tmp/mcp-client-evidence-gate.zip -d ~/.claude/skills && rm /tmp/mcp-client-evidence-gate.zipFree skills install directly. Paid skills require purchase - use the download button above after buying.
Reviews
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
No reviews yet - be the first to share your experience.
Only users who have downloaded or purchased this skill can leave a review.
Security Scanned
Passed automated security review
Permissions
Allowed Hosts
File Scopes
Tools Used note: "Reads local MCP server configs, fixtures, and package files. Writes local compatibility receipts, logs, and evidence outputs. Does not require browser access, network access, secrets, or environment variable access for the verified v0.1 local evidence workflow." _____________________________________________________________________ Note on HOSTS: Skill doesn't need to call API as the runner is Codex or Qwen cli.
Requires Node.js 18+. Verified with Codex CLI v0.142.2 and Qwen Code v0.19.2 for stdio discovery evidence. Other clients and transports are marked by evidence tier when not directly executed.
Frequently Asked Questions
Learn More About AI Agent Skills
More Premium Skills
cinematic-sites
Turn any basic business URL into a high-end cinematic landing page with AI-generated 4K assets and GSAP animations.
endless-loop
Autonomous research and task loop that builds on previous findings to solve complex objectives while you sleep.
skill-router-2
Automatically detect, load, and stack the perfect skills combo for any user request.

inline-comment
Best way to steer your agents, effortlessly.