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.

DimensionProtocol LauncherType-safe one-click links for protocol-based appsMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS33 / 100 · D79 / 100 · B
Reliability3 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation10 / 2018 / 20
Setup experience4 / 2015 / 20
Best for
  • TypeScript developers embedding one-click launch links in websites, documentation, or automation flows
  • Modern Node.js or bundler projects that benefit from on-demand imports and tree-shaking
  • Teams wrapping supported protocol links with type-safe APIs
  • 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 looking for an MCP server whose tools can be connected and called directly
  • Deployments requiring a standalone MCP server, remote transport, or server-side authentication
  • Environments where the target application does not support the relevant protocol or URL scheme
  • 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 library itself has no explicitly documented system permissions
  • Generated links may ask a target app to open files, projects, settings, or imported configuration; actual permissions depend on the target app and operating system
  • 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
  • Generated links may contain API keys, commands, parameters, or other sensitive configuration; inspect URLs before sharing
  • Opening a link may launch a local app, import settings, or install MCP configuration; use trusted sources and targets
  • The README does not document the complete security boundaries, permission model, or compatibility matrix for each integration
  • 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