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.

Dimensionn8n MCP Client NodeConnect and call MCP servers in n8n workflows.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS40 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions6 / 2018 / 20
Maintenance7 / 2016 / 20
Documentation11 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • n8n users who want to integrate MCP tools into their automation flows.
  • Developers building AI agents that need to call external tools and data sources.
  • Teams that need to quickly connect to various MCP servers, whether local (via npx) or remote (HTTP).
  • 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 who need a direct programming interface rather than a graphical workflow.
  • Users without an n8n environment who just want a standalone MCP client.
  • Users who rely on SSE transport and cannot upgrade to HTTP Streamable (SSE is deprecated).
  • 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 the ability to install community nodes in n8n.
  • Requires setting the environment variable N8N_COMMUNITY_PACKAGES_ALLOW_TOOL_USAGE=true to use the node as a tool.
  • With STDIO transport, it can execute arbitrary local commands (as defined by the user's command setting), potentially with system permissions.
  • Can make network requests to configured MCP servers, including sending additional headers.
  • 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
  • STDIO commands can execute arbitrary local commands; if misconfigured (e.g., using untrusted servers), it may compromise the system.
  • SSE transport is deprecated and no longer updated, potentially having security vulnerabilities.
  • Environment variables (like API keys) may be stored in n8n credentials; if the n8n instance is not secure, there is a risk of exposure.
  • Running third-party MCP servers (e.g., downloaded via npx) may introduce insecure dependencies.
  • 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 DesktopClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools60