Log inSubmit server
N8n MCP logo

N8n MCP

Generate, validate, debug, compare, and manage n8n workflows through MCP tools.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install N8n MCP

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "n8n-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@automatelab/n8n-mcp"
      ],
      "env": {
        "N8N_API_URL": "YOUR_VALUE_HERE",
        "N8N_API_KEY": "YOUR_VALUE_HERE",
        "N8N_MCP_READ_ONLY": "YOUR_VALUE_HERE",
        "N8N_MCP_DISABLED_TOOLS": "YOUR_VALUE_HERE",
        "N8N_MCP_ALLOWED_WORKFLOW_IDS": "YOUR_VALUE_HERE",
        "N8N_MCP_ALLOWED_TAGS": "YOUR_VALUE_HERE"
      }
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Values are written into the snippet above so you can paste it as is. They never leave your browser.

Automated check passed— started and listed 12 tools correctly (9d ago).

Overview

The n8n-mcp MCP server gives AI agents tools for generating n8n workflows, scaffolding custom nodes, linting workflow JSON, and diagnosing executions. Stateless tools operate on supplied JSON, while REST-backed tools connect to a live n8n instance using an API URL and key. Reach for it when an agent needs to create workflows, check AI Agent wiring, investigate failed runs, or manage selected workflows and executions.

Use cases

  • Generate n8n workflows from plain-English requirements
  • Lint workflow JSON before importing it into n8n
  • Diagnose failed executions and dropped items
  • Compare workflow revisions and inspect execution timelines
  • Manage selected live workflows through the n8n API

Key features

  • Plain-language workflow generation with AI Agent topology detection
  • Custom n8n node TypeScript scaffolding
  • Workflow linting with more than 20 rules
  • Semantic workflow diffs and node replay generation
  • Per-node execution diagnosis and timeline reporting
  • Live workflow and execution management through the n8n API

Tools12

What N8n MCP lets your agent do. Expand a tool for its parameters.

Verified live~2.3k tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

7/7 checks healthy over the last 39d

What it can do

From the 12 tools this server returned when we ran it; 12 declare their own safety hints.

Runs commands · 1Handles credentials · 4Makes network requests · 7Read-only tools · 11
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceNot published
Package age157 days
Maintainers1

Observed 2026-10-14 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 12d ago via OSV.dev · @automatelab/n8n-mcp (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars14Stargazers on the source repository.
npm downloads346Package downloads in the last 30 days.
Last commit3d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed12Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How N8n MCP works

What n8n-mcp MCP server does

The n8n-mcp MCP server connects AI agents with n8n workflow data and provides focused tools for creation, validation, comparison, and troubleshooting. Its stateless capabilities do not require a running n8n instance: an agent can generate workflow JSON from a plain-language request, produce a TypeScript INodeType file for a custom n8n package, lint workflow JSON, compare two workflows, explain a failed execution, create a node-specific replay workflow, or produce an execution timeline.

The server also exposes operations for live n8n instances. Agents can list workflows with filters, retrieve a workflow by ID, create a workflow, change its active state, and browse executions. These live operations require n8n API access.

How it works

The n8n-mcp MCP server exposes tools through MCP using dot-notation groups such as workflow.*, node.*, and execution.*. Each tool provides an output schema and MCP annotations describing properties such as read-only, destructive, or idempotent behavior.

For generation, the agent supplies a natural-language description and receives workflow JSON suitable for importing into n8n. The generator detects AI-agent requirements and can represent LangChain-related connections, including ai_languageModel, ai_memory, and ai_tool. Linting checks more than 20 conditions, including deprecated node types, missing AI Agent language models, webhook identifiers, IF node schema issues, and invalid connections across connection types.

Execution analysis accepts execution JSON. The explanation tool reports node-level findings and hints, while the timeline tool summarizes start times, durations, item counts, and errors. Replay builds a standalone workflow focused on a selected node. The diff tool identifies changes to nodes, connections, and settings.

Setup and configuration

Install Node.js 20 or later, then install the package globally with npm install -g @automatelab/n8n-mcp, or launch it with npx -y @automatelab/n8n-mcp from an MCP host configuration. Cursor and Claude Desktop examples are provided in the repository. The four stateless tools can run without environment variables.

Set N8N_API_URL and N8N_API_KEY to enable the live-instance tools. The API key is created in n8n under Settings, API, and Create API key. The repository also documents Docker, Claude Desktop DXT, Render, Railway, and Fly.io deployment options.

Runtime policies can restrict access without modifying the server. N8N_MCP_READ_ONLY=1 disables workflow creation, activation, and node scaffolding. N8N_MCP_DISABLED_TOOLS prevents selected tools from registering, while N8N_MCP_ALLOWED_WORKFLOW_IDS and N8N_MCP_ALLOWED_TAGS limit which workflows the REST tools can access or list.

Limitations and notes

The n8n-mcp MCP server does not require a live n8n instance for its stateless analysis and generation tools, but workflow listing, retrieval, creation, activation, and execution browsing depend on valid API configuration. Creating or activating workflows changes the connected n8n instance unless runtime restrictions disable those operations.

Tool names use dot-notation in the current release, replacing earlier n8n_* snake-case names. Existing prompts, scripts, or agent skills that reference the old names need updating. The repository includes example workflows for Stripe-to-Slack with Google Sheets and RSS-to-Discord, but importing them still happens through n8n's Import from File flow.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about N8n MCP

n8n-mcp is an MCP server that connects AI agents to n8n and provides tools to generate workflows, scaffold custom nodes, lint workflow JSON, diagnose executions, compare workflows, and manage live workflows through the n8n API. Stateless analysis works without a connected n8n instance, while live operations require API configuration.

Install Node.js 20 or later, then run `npm install -g @automatelab/n8n-mcp` or launch it with `npx -y @automatelab/n8n-mcp`. Configure the resulting command in your MCP host. The repository also documents Docker and several hosted deployment options.

Yes, n8n-mcp works with Cursor. Add it to Cursor's `~/.cursor/mcp.json` using the npx command, and optionally provide `N8N_API_URL` and `N8N_API_KEY` for live n8n tools. Stateless tools work without those environment variables.

Yes, n8n-mcp can manage a live n8n instance when `N8N_API_URL` and `N8N_API_KEY` are configured. Its live tools list, fetch, create, and activate workflows, and browse executions. Runtime policy variables can restrict workflow IDs, tags, or selected operations.

Related MCP servers

All in Developer Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewN8n MCP AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/n8n-mcp?style=directory)](https://allmcps.com/mcp/n8n-mcp)
HTML Embed
<a href="https://allmcps.com/mcp/n8n-mcp"><img src="https://allmcps.com/api/badge/n8n-mcp?style=directory" alt="N8n MCP on AllMCPs" /></a>