$ loading_
Audit MCP servers for conformance, tool usability, and error handling quality.
Copy the install command and let the AI configure it · recommended for beginners
No copy-paste install info for "MCProbe" yet — see the docs or source repo.
Use MCProbe to connect to this MCP server via stdio with `node server.js`. Audit every tool schema for usability, call each tool with intentionally broken inputs, and return a 0-100 score, per-dimension breakdown, and fix recommendations.
A Markdown audit report with an overall score, dimension scores, issues found, and improvement recommendations.
Audit these two MCP servers, one over HTTP and one over stdio. Compare their schema design, error handling, and protocol conformance, then summarize which is better suited for AI agents.
A comparison showing scoring differences, key issues, and a conclusion on agent suitability.
Run a pre-release audit on the current MCP server version. Focus on tool parameter schema clarity, robustness of error responses, and behavior under invalid inputs, then output Markdown suitable for CI review.
An audit result suitable for release review or CI, helping the team quickly identify compatibility and quality risks.
Scan configured MCP servers locally and generate inventory with risk scores.
Build, integrate, and debug MCP clients and related tooling.
Run dev checks and get compact error summaries for faster debugging.
Diagnose Linux systems and control desktop hardware with compact, safe JSON output.
Audit any MCP server.json for official MCP spec compliance.
Analyze MCP tool security risks, detect malicious behavior, and provide risk scores.