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.

DimensionContextLocal-first documentation for AI agents — offline, instant, private doc retrieval.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS56 / 100 · C79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions10 / 2018 / 20
Maintenance9 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience14 / 2015 / 20
Best for
  • Developers who need fast, reliable, and private documentation retrieval
  • Developers using popular libraries like Next.js, React, Prisma
  • AI agent users in offline or low-latency environments
  • Teams that need to share custom documentation packages
  • 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
  • Users who need automatic updates for all packages (versions are fixed and need manual updates)
  • Teams that prefer not to install through a global package manager
  • Users expecting a cloud-hosted service
  • 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
  • Read/write to ~/.context directory (stores docs and auth data)
  • Network access (for first-time package downloads and registry queries)
  • Communication with clients via stdio or HTTP
  • 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
  • Registry packages may contain outdated or inaccurate content (community-maintained)
  • Installed packages consume disk space (a few MB each)
  • In HTTP mode, if not restricted to localhost, could be exposed to other clients on the network
  • 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, Claude Desktop, Cursor, Codex, VS Code, Windsurf, Zed, Goose, OpenCodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools40