paiml-mcp-agent-toolkit

Overview

Pragmatic Multi-language Agent Toolkit (PMAT) offers comprehensive code analysis capabilities through its MCP server implementation. It provides 19 tools for AI agents to analyze code quality, generate technical debt grading, perform mutation testing, and create AI-optimized context. Built in Rust with extensive test coverage (99.66%) and active maintenance, PMAT integrates with Claude Code and other AI coding assistants. The toolkit follows Toyota Way quality principles and includes features like Git History RAG, semantic search, and compliance governance across 20+ programming languages.

Try asking AI

After installing, here are 5 things you can ask your AI assistant:

• context

  Generate AI-ready context for code analysis

  Try:Generate LLM-optimized context for this codebaseTry:Create context including test files
• analyze

  Analyze code quality metrics including complexity and technical debt

  Try:Analyze technical debt in the projectTry:Check code complexity issues
• repo-score

  Score repository health across 11 categories (0-289 scale)

  Try:Score the repository healthTry:Get detailed repository metrics
• mutate

  Run mutation testing to validate test suite effectiveness

  Try:Run mutation testing on the src directoryTry:Check test coverage with mutation testing
• query

  Search code with semantic analysis and git history

  Try:Search for "error handling patterns"Try:Find functions related to cache invalidation
• comply

  Run compliance governance checks across code quality and best practices

  Try:Run all compliance checksTry:Check for technical debt regression
• kaizen

  Autonomous continuous improvement - scan, auto-fix, and commit changes

  Try:Run kaizen analysis with dry-runTry:Apply auto-fixes and commit improvements
• extract

  Extract function boundaries with metadata

  Try:Extract functions from src/lib.rsTry:List all functions with visibility info
• infra-score

  Score CI/CD infrastructure quality (0-100 scale)

  Try:Evaluate CI/CD pipeline qualityTry:Get infrastructure health report
• hooks

  Manage Git hooks for quality enforcement

  Try:Install pre-commit hooksTry:Check hook installation status
• prompt

  Run pre-configured AI prompts for TDD and quality enforcement

  Try:List available promptsTry:Run code coverage enforcement prompt
• tdg-baseline

  Create technical debt baseline and check for regressions

  Try:Create TDG baselineTry:Check for quality score degradation

Comparable tools

Installation

cargo install pmat

pmat mcp

{
  "mcpServers": {
    "pmat": {
      "command": "pmat",
      "args": ["mcp"]
    }
  }
}

FAQ

What languages does PMAT support?

PMAT supports 20+ languages including Rust, TypeScript, Python, Go, Java, C/C++, Lua, Lean, and various MLOps model formats.

How does PMAT ensure quality in its own codebase?

PMAT follows Toyota Way principles with 21,200+ passing tests, 99.66% coverage, >80% mutation score, and explicit quality commitments with CI enforcement.

Compare paiml-mcp-agent-toolkit with