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.

DimensionMetaMCPA self-hosted gateway that aggregates MCP servers into unified endpoints.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS60 / 100 · C79 / 100 · B
Reliability10 / 2012 / 20
Security and permissions12 / 2018 / 20
Maintenance10 / 2016 / 20
Documentation15 / 2018 / 20
Setup experience13 / 2015 / 20
Best for
  • Developers and organizations that need self-hosted MCP infrastructure.
  • Teams that centrally manage multiple MCP servers, namespaces, endpoints, and access keys.
  • Deployments that need authentication, rate limiting, and tool-selection controls around MCP access.
  • 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 who only need a single MCP server without aggregation or gateway features.
  • Deployments that cannot run Docker or provide the required runtime environment.
  • STDIO-only client environments where a local proxy cannot be used.
  • 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
  • Access to configured upstream MCP servers.
  • Permission to start configured commands and dependencies for STDIO MCP servers.
  • Access to container environment variables containing secrets and other configuration.
  • Handling of sessions, API keys, or OIDC login data when authentication is enabled.
  • Network access, Docker, and persistent PostgreSQL storage for deployment.
  • 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
  • Misconfiguration can expose multiple upstream MCP servers or tools through one public endpoint.
  • Poor handling of environment variables or API keys can disclose credentials.
  • Public endpoints may face unauthorized calls, excessive traffic, or misuse of upstream tools.
  • Rate-limit counters are stored in memory, and each cluster machine counts traffic independently.
  • Running STDIO servers and their dependencies expands the container's execution and network-access scope.
  • 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 clientsCursor, Claude DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools00