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.

DimensionClaude Code Source Restoration (CC)A runnable TypeScript source reconstruction of Claude Code CLI from source maps, for research only.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS14 / 100 · D79 / 100 · B
Reliability1 / 2012 / 20
Security and permissions4 / 2018 / 20
Maintenance2 / 2016 / 20
Documentation3 / 2018 / 20
Setup experience4 / 2015 / 20
Best for
  • Developers interested in Claude Code's internals
  • Researchers analyzing large TypeScript projects
  • Technical users who want to study or extend Claude Code's source
  • 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
  • Production use, as it is unofficial and incomplete
  • Users seeking official support or stability
  • Commercial use, as copyright belongs to Anthropic
  • 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
  • This repo itself doesn't require API permissions, but running Claude Code features may need an Anthropic API key
  • Filesystem read/write permissions to install dependencies and run the CLI
  • Network access to call Anthropic API or fetch resources
  • 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
  • The reconstructed version may contain unknown bugs or security vulnerabilities; not recommended for production
  • Source may be incomplete; some features may be missing or behave incorrectly
  • Copyright risk; for personal research and study only, not for commercial use
  • 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 Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00