@ratamaha-git
Basic information
Generate n8n workflow JSON (including LangChain AI agents), scaffold custom TypeScript nodes, and lint workflows for missing credentials, deprecated types, and broken connections.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"n8n": {
"command": "npx",
"args": [
"-y",
"@automatelab/n8n-mcp"
],
"env": {
"N8N_API_URL": "",
"N8N_API_KEY": ""
}
}
}
}Plain-English description → workflow JSON. Detects AI-agent intent.
Description → single `INodeType` TypeScript file for a custom n8n package.
Workflow JSON → list of errors and warnings.
Failed execution JSON → per-node diagnosis with hints.
Paginate workflows; filter by active/tags/name.
Fetch a workflow by id.
POST a workflow. Strips read-only fields.
Flip active on/off.
Browse executions; pass `includeData: true` for the full body.
Automatelab N8n is an MCP (Model Context Protocol) server that gives Claude, Cursor, and other MCP-compatible agents nine tools for working with n8n: scaffold a custom node, generate workflow JSON, lint workflows, diagnose failed executions, and drive a live n8n instance via REST. It is designed for developers who need debugging and first-run correctness when building n8n automations with AI assistance.
Install the server globally with npm install -g @automatelab/n8n-mcp, then configure it in your MCP host (e.g., Cursor's mcp.json or Claude Desktop's claude_desktop_config.json) by specifying the command npx -y @automatelab/n8n-mcp. Optionally set environment variables N8N_API_URL and N8N_API_KEY to enable the five live-instance tools; the four stateless tools work without them. After restarting the host, the nine n8n_* tools appear in the MCP panel.
Automatelab N8n focuses on debugging and first-run correctness. While other servers emphasize breadth with many tools and indexed node catalogs, this server specializes in diagnosing failed executions, linting workflow JSON for subtle failures, and generating AI Agent clusters with proper connection topology.
No. Four of the nine tools (`n8n_generate_workflow`, `n8n_scaffold_node`, `n8n_lint_workflow`, `n8n_explain_execution`) are stateless and work without any connection to an n8n instance. The five REST tools require setting `N8N_API_URL` and `N8N_API_KEY`.
In your n8n instance, go to **Settings → API → Create API key** and copy the generated key. Set it as the `N8N_API_KEY` environment variable in your MCP host configuration.
It requires Node.js version 20 or later.
Yes. The `examples/` directory ships with two ready-to-import workflows: Stripe webhook to Slack and Google Sheets, and RSS feed to Discord. Import them
A Cloudflare-powered MCP (Model Context Protocol) Server that allows you to search and query your GitHub starred repositories using natural language.
Node.js/TypeScript MCP server for Atlassian Jira. Equips AI systems (LLMs) with tools to list/get projects, search/get issues (using JQL/ID), and view dev info (commits, PRs). Connects AI capabilities directly into Jira project management and issue tracking workflows.
A Git MCP server for AI agents. STDIO & Streamable HTTP.
MCP server that enables AI assistants to interact with Linear project management system through natural language, allowing users to retrieve, create, and update issues, projects, and teams.
A Go-based MCP (Model Control Protocol) connector for Jira that enables AI assistants like Claude to interact with Atlassian Jira. This tool provides a seamless interface for AI models to perform common Jira operations including issue management, sprint planning, and workflow tra
Comments