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.

DimensionDocker MCP GatewayDocker's official MCP gateway CLI plugin for managing and running MCP servers.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS68 / 100 · C79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions15 / 2018 / 20
Maintenance18 / 2016 / 20
Documentation14 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • Developers using Docker Desktop who want to simplify MCP server deployment and management.
  • Teams needing to manage multiple MCP servers under a single gateway with consistent configuration and monitoring.
  • Environments requiring containerized MCP servers to minimize host privileges.
  • 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
  • Developers not using Docker.
  • Scenarios needing direct execution of local npx or uvx servers without containerization.
  • Users seeking a lightweight MCP client independent of Docker Desktop.
  • 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 access to the Docker daemon to run and manage containers.
  • Reads and writes local configuration files (e.g., ~/.docker/config.json).
  • Accesses Docker Desktop's secret management for storing credentials.
  • May initiate OAuth flows, requiring 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
  • Container images may contain malicious code; be cautious with untrusted MCP servers.
  • Improper secret management could leak API keys.
  • Misconfiguration of the gateway can lead to client connection failures or incorrect tool access.
  • Potential version compatibility issues due to reliance on Docker Desktop and CLI plugin.
  • 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