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.

DimensionMDN MCP ServerMDN's official experimental MCP server for web search, docs, and browser compatibility dataMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS53 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions12 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation11 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Web developers who need accurate, current web platform documentation
  • Coding agents aiming to reduce inaccuracies caused by outdated LLM training data
  • 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 require strict data-privacy guarantees and want no query logging whatsoever
  • Production workflows requiring a stable, guaranteed-uptime API, since this server is experimental and may be withdrawn at any time
  • 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
  • The server itself does not require access to local files or a codebase
  • Using the remote server sends query content to Mozilla's servers
  • 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 README states that query data is stored for analytics; it is not linked to identifying user information, but private details a user shares with the LLM could inadvertently be included in logged queries
  • As an experimental project, the server may be withdrawn at any time, making it unsuitable for dependencies requiring long-term stability
  • Use of the remote server requires compliance with Mozilla's Acceptable Use Policy
  • 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 CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00