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.

DimensionAgentThe unified MCP runtime that aggregates your MCP servers and adds a thinner agent-facing workflow.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS43 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions5 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience12 / 2015 / 20
Best for
  • Users with Codex, Claude, Cursor, or similar agents who want to keep MCP as backend but reduce context burden.
  • Teams needing consistent MCP configuration across multiple clients and projects.
  • 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
  • Native HTTP MCP clients that want direct access without project context.
  • Simple single-server scenarios where an additional runtime dependency is undesirable.
  • 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
  • May make network connections to upstream MCP servers.
  • May read and write local filesystem for configuration and caching.
  • May spawn and manage subprocesses (for stdio backends).
  • 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 an aggregated runtime, it introduces an extra point of failure.
  • May expose a broader tool surface than intended if filters or presets are not configured properly.
  • Template server resolution depends on client context and may lead to unexpected behavior.
  • 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, Codex, CursorClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools30