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 Workflow BuilderManage n8n workflows through natural language, connecting AI assistants to your automation platform.MartinLoop MCP ServerAn independent control layer that gives AI coding agents budgets, brakes, and receipts
FMRS44 / 100 · D79 / 100 · B
Reliability5 / 2012 / 20
Security and permissions7 / 2018 / 20
Maintenance8 / 2016 / 20
Documentation13 / 2018 / 20
Setup experience11 / 2015 / 20
Best for
  • Teams using n8n for automation who want to leverage AI assistants to simplify workflow management.
  • Users who want to create workflows through conversational interfaces without directly using the n8n Web UI.
  • Developers looking to integrate AI assistants into their existing n8n workflows.
  • 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 without an n8n instance or API key.
  • Those seeking a full low-code visual interface rather than AI-driven management.
  • Users requiring direct support or maintenance from the official n8n product team.
  • 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 your n8n instance URL (`N8N_HOST`) and an API key (`N8N_API_KEY`).
  • The API key should have appropriate permissions, typically read/write access to workflows, executions, tags, and audits.
  • The server communicates directly with your n8n instance; it does not store data but requires 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
  • API key leakage could lead to unauthorized access to your n8n workflows and data.
  • Misconfiguration could result in unintended workflow modifications, deletions, or executions.
  • Involving automation actions should first be tested on a small scale.
  • When using third-party hosted services (like Smithery.ai), consider data privacy implications.
  • 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, Cline, Continue, Other MCP-compatible clientsClaude Code, Codex, Gemini CLI, Cursor, VS Code, GitHub Copilot, Continue
Tools150