M
MCP Directory CURATED DIRECTORY
911 MCP servers indexed
中文
← Back to directory
COMPARE UP TO 4 SERVERS

Compare MCP servers

Compare scores, permissions, risks, and fit in one decision-focused table.

DimensionPare PythonStructured Python tool output (ruff, mypy, pip, uv, black, pytest) as typed JSON.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS39 / 100 · D79 / 100 · B
Reliability6 / 2012 / 20
Security and permissions6 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation8 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • AI coding agents primarily working in the Python ecosystem.
  • Developers looking to save tokens when integrating development tools.
  • Scenarios requiring reliable integration with ruff, mypy, pip, uv, black, pytest.
  • Engineering teams scaling AI coding agents while controlling spend
  • Platform teams that need auditable, rollback-aware agent execution records
  • Organizations using multiple agents (Claude, Codex, Gemini) under one governed flow
Not for
  • Projects that do not use Python tools.
  • Tasks requiring interactive terminal sessions (e.g., certain pytest debug modes).
  • Environments without Node.js 20+ or npm.
  • Developers who just want a simple code-completion helper without run governance
  • Teams unwilling to accept local JSONL run records with HMAC signing
  • Environments without a supported adapter (Claude/Codex/Gemini CLIs, direct provider, or verifier-only)
Required permissions
  • Execute Python tools (ruff, mypy, pip, uv, black, pytest).
  • Access filesystem to run these tools.
  • Network access if pip/uv require it.
  • Read/write access to the configured repo root (writable scope restrictable via --allow-path/--deny-path)
  • Ability to invoke the chosen agent CLI (Claude/Codex/Gemini, etc.) and its underlying model account
  • Local disk writes for run records, receipts, and share outputs (share/run-receipt., etc.)
  • Execution of user-configured verifier commands (e.g. npm test)
Risks and side effects
  • Executing arbitrary Python tools may have unintended side effects (e.g., installing packages).
  • Tool results may be inaccurate if environment paths are not correctly configured.
  • Dependency on external tool versions that may alter output formats.
  • Verifier commands are executed; poorly chosen verifier commands carry security risk despite preflight policy checks
  • Cost and token figures may be estimates (labeled with provenance) and should not be treated as settled accounting
  • Receipt integrity must be verified before use as trustworthy evidence; missing rollback evidence is flagged as EVIDENCE_BOUNDARY
  • Policy defaults come from martin.config.yaml and can be overridden by CLI flags; misconfiguration can loosen safety boundaries
Supported clientsClaude Desktop, Claude Code, CursorClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00