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.

DimensionMCP TypeScript SDKThe official TypeScript SDK for building MCP servers and clientsMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS63 / 100 · C79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions12 / 2018 / 20
Maintenance14 / 2016 / 20
Documentation14 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • TypeScript developers building MCP servers or clients
  • Projects requiring Node.js, Bun, or Deno runtime support
  • Projects needing optional middleware for web framework integration
  • 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 seeking ready-made business tools instead of an SDK
  • Users seeking a preconfigured desktop-client connection
  • Projects outside the TypeScript or JavaScript ecosystem
  • 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
  • Permissions depend on the application and tool implementations built with the SDK
  • HTTP integrations may require handling requests, Host header validation, and JSON request bodies
  • OAuth permissions depend on the specific client or server implementation
  • 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 SDK does not define business-specific permissions; practical risk depends on the data and operations exposed by built tools
  • HTTP security depends on the application's host validation, authentication, and deployment configuration
  • The main branch is v2, so users must account for differences from the v1 API and documentation
  • 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