Enterprise DNA
M MCP Servers Developer low

AutomateLab-tech/n8n-mcp

by Various

Debugging-first MCP server for n8n. Tools for workflow generation, linting, per-node execution diagnosis, and driving live n8n instances. Built for AI agents.

A

MCP

AutomateLab-tech/n8n-mcp

Added 7 June 2026

#ai-agent #ai-agents #ai-tools #claude #claude-code-plugin #mcp #model-context-protocol #n8n

Overview

An open-source MCP server that connects AI agents to n8n. It provides tools for generating workflows, linting them, diagnosing per-node execution, and controlling live n8n instances. Designed for a debugging-first workflow.

Best for

Best for
Developers who want to use AI agents to create and debug n8n workflows programmatically

Use cases

  • Generate n8n workflows from natural language prompts
  • Debug and fix node execution errors with step-by-step analysis
  • Lint existing workflows for compliance with best practices

Notes

An open-source MCP server that connects AI agents to n8n. It provides tools for generating workflows, linting them, diagnosing per-node execution, and controlling live n8n instances. Designed for a debugging-first workflow.

7 stars on GitHub. Last updated 2026-05-31. Licensed MIT.

Use cases

  • Generate n8n workflows from natural language prompts
  • Debug and fix node execution errors with step-by-step analysis
  • Lint existing workflows for compliance with best practices

Pros

  • Built specifically for agent-driven debugging and workflow creation
  • Integrates directly with n8n’s live instances
  • Open-source and written in TypeScript

Cons

  • Very low adoption (7 stars) indicating limited testing or maturity
  • Depends on the Model Context Protocol, which is not standard across all AI agents
  • Requires running an MCP server, adding infrastructure overhead

Indexed from awesome-mcp-servers-punkpeye and enriched against its public facts.

Pros

  • Built specifically for agent-driven debugging and workflow creation
  • Integrates directly with n8n's live instances
  • Open-source and written in TypeScript

Cons

  • Very low adoption (7 stars) indicating limited testing or maturity
  • Depends on the Model Context Protocol, which is not standard across all AI agents
  • Requires running an MCP server, adding infrastructure overhead