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.

DimensionMCPOExpose MCP tools as OpenAPI services instantly.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS53 / 100 · D79 / 100 · B
Reliability8 / 2012 / 20
Security and permissions8 / 2018 / 20
Maintenance11 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • LLM applications and developers that need MCP tools over HTTP
  • Teams using OpenAPI tools, SDKs, or UIs
  • Deployments requiring multi-server configuration, hot reload, or OAuth 2.1
  • 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
  • Clients that only need direct native MCP stdio communication
  • Deployments unwilling to manage API keys, network ports, or proxy security
  • Other protocols or integrations not documented in the source
  • 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
  • It must execute the specified MCP server command or connect to the specified SSE or Streamable HTTP endpoint
  • It must listen on the configured HTTP port
  • OAuth 2.1 may require browser authorization, a callback port, and, with file storage, write access to ~/.mcpo/tokens/
  • 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 exposed HTTP service should use an API key; the README demonstrates API keys as startup arguments
  • The proxy makes MCP tools available to callers that can reach the HTTP service, so port and reverse-proxy settings require care
  • OAuth tokens may be stored under ~/.mcpo/tokens/; protect that directory in deployment
  • Commands, endpoints, and headers in the configuration affect proxy targets and credentials
  • 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 clientsOpen WebUIClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00