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.

DimensionFuck-U-CodeLet bad code have nowhere to hide – assess the legacy-mess level of your code and output a beautiful report.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS45 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions7 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation11 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Developers and teams wanting a quick snapshot of their codebase health.
  • Users of AI coding assistants (like Claude Code) who want automated code review.
  • Projects needing multi-language support (14 languages).
  • Developers who appreciate witty and blunt feedback.
  • 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
  • Teams requiring serious, professional, and emotionless code reviews.
  • Enterprise users needing deeply customizable analysis rules (e.g., custom metrics).
  • Organizations managing large-scale codebases that need more powerful enterprise tools.
  • Environments where profanity or informal tone is inappropriate.
  • 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
  • File system access to read code files for analysis.
  • Optional: Access to external AI APIs (e.g., OpenAI, Anthropic) for AI review.
  • Write access to configuration files (~/.fuckucoderc.json) and possibly MCP config files (e.g., .mcp.json).
  • Network access for updates or external API calls.
  • 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
  • AI review features send code snippets to external services (e.g., OpenAI), which may raise privacy concerns.
  • Analysis results may include false positives or missed issues, so should not be the sole quality metric.
  • Tool name and feedback style may be unprofessional for formal settings.
  • Misconfiguration can prevent the MCP server from starting.
  • 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 DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools20