Skip to content

AI Developer Tool · TypeScript

checkmcp

Vendor-neutral quality/security/context-cost audit & score for any MCP server

What it is

CheckMCP is a tool for auditing and scoring MCP servers across security, design, and cost dimensions. It provides a CLI, HTTP interface, MCP server mode, and a self-hosted security gateway for evaluating and protecting MCP-based AI systems.

  • ai
  • ai-agents
  • claude
  • cli
  • devtools
  • llm
  • mcp
  • mcp-server
  • model-context-protocol
  • owasp
Scored at6d272b111 Nov 2026Changes since

Merit describes the code at this commit. Later pushes count once the owner rescans. How merit is scored

Where it counts

  • AI Agents60%
  • MLOps50%
  • NLP & LLMs40%
  • Data Science30%
  • Machine Learning20%

How much of the project is about each field, as scoring counts it. It ranks in the field it is most about.

What the judge found

Read from the project's code at its scored commit.

Strengths5

  • Comprehensive auditing across 7 relevant dimensions for MCP servers.
  • Zero-stdlib-dependency core for reduced attack surface and ease of deployment.
  • Combines static analysis with dynamic behavioral evaluation (`--evals`) for thorough security checking.
  • Provides a self-hosted gateway for inline security in private infrastructure.
  • Well-tested with CI and multiple test files covering unit, integration, and end-to-end scenarios.

Limitations

The owner keeps this project's limitations private.

Around it on the AI Agents board

Whole board
  1. 07atheneumLibrary / Framework · Rust70.9/100AdvancedLuiz Cesar Spies
  2. 08DronaLibrary / Framework · Python70.8/100AdvancedSai Kannadkar
  3. 09checkmcpAI Developer Tool · TypeScript68.8/100AdvancedH129hj
  4. 10kazmaAgent System · Python68.6/100AdvancedMubder Alfaris
  5. 11la-caja-mcpLibrary / Framework · Python68.2/100Advanceddeviceargent

More from H129hj