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.

DimensionMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receiptsFastMCPA TypeScript framework for building MCP servers
FMRS79 / 100 · B75 / 100 · B
Reliability12 / 2011 / 20
Security and permissions18 / 2016 / 20
Maintenance16 / 2017 / 20
Documentation18 / 2017 / 20
Setup experience15 / 2014 / 20
Best for
  • 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
  • Developers who want to build MCP servers quickly without low-level details
  • Scenarios requiring built-in authentication, streaming output, custom routes, etc.
  • Developers using TypeScript who value type safety
Not for
  • 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)
  • Scenarios requiring support for the latest MCP specification (2026-07-28)
  • Advanced users needing full control over low-level implementation
  • When maximum flexibility is needed, prefer the official SDK
Required permissions
  • 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)
  • File system access (in Node.js environments)
  • Network access for OAuth and remote requests
  • Environment variables for client secrets, etc.
Risks and side effects
  • 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
  • Legacy protocol may not be compatible with future specifications, possibly breaking with latest clients
  • Dependency on third-party libraries introduces supply chain risks
  • Custom authentication logic might introduce security vulnerabilities
Supported clientsClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00