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 CLIA lightweight CLI to interact with MCP servers.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS64 / 100 · C79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions12 / 2018 / 20
Maintenance14 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • AI coding agents that need lightweight MCP server integration.
  • Developers who prefer terminal-based interactions.
  • Users needing efficient, scriptable access to MCP tools.
  • 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 requiring a graphical interface.
  • Scenarios not involving the MCP protocol.
  • Applications needing persistent connections or heavy session management (CLI is designed for one-off requests).
  • 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
  • Read and write MCP server configuration as specified in config file.
  • Spawn subprocesses via stdio (e.g., npx).
  • Establish network connections to remote MCP servers if configured.
  • Create temporary Unix sockets for connection pooling (daemon mode enabled by default).
  • 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
  • Sensitive information (e.g., API keys) in config may be stored in plaintext.
  • MCP servers launched may execute arbitrary commands, especially from untrusted sources.
  • Connection keep-alive may hold resources if not idle-timeout.
  • Supply chain risks when using npm/npx packages as server commands.
  • 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 Desktop, Gemini CLI, OpenCode, Claude CodeClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools30