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 NestNestJS module to effortlessly create MCP serversMartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS51 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance12 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience10 / 2015 / 20
Best for
  • NestJS developers wanting to integrate AI tools seamlessly into existing backends
  • Teams needing secure, scalable, and testable MCP servers
  • Projects requiring fine-grained authorization and observability within a microservice architecture
  • 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
  • Non-NestJS users, as it is strictly NestJS-based
  • Developers wanting to use different transports like SSE (only Streamable HTTP and STDIO are supported)
  • Those seeking a no-code solution to create MCP servers without writing TypeScript or NestJS code
  • 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
  • Requires a Node.js and npm environment
  • When running STDIO transport, the process stdout must be reserved for the protocol
  • For HTTP transport, an accessible endpoint is needed; external authorization servers (like OAuth) may require network access
  • 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
  • As a relatively new module, its API may evolve (e.g., migration from v1 to v2)
  • When using external authorization servers, careful handling of OAuth flows is required
  • Depending on ctx.reportProgress may be ineffective on legacy stateless clients with stateful sessions
  • 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