n8n MCP Server

How to use

Connect your MCP client to an MCP server to start querying node data, templates, and workflow management capabilities. You can run the server locally for development or deploy it headlessly in the cloud. When you connect, your AI agent can access real-time node details, documentation, and pre-validated configurations to help you design and test workflows.

How to install

Prerequisites vary by deployment method. Ensure you meet the minimum requirements for Node.js, Docker, or the ability to run commands locally. Follow the flow that matches how you want to run the MCP server.

# Prerequisites (example for local quick setup)
# - Node.js installed on your system
# - Git installed for cloning repositories (optional)
```

```json
{
  "mcpServers": {
    "n8n_mcp_npx": {
      "command": "npx",
      "args": ["n8n-mcp"],
      "env": {
        "MCP_MODE": "stdio",
        "LOG_LEVEL": "error",
        "DISABLE_CONSOLE_OUTPUT": "true"
      }
    }
  }
}
```

```json
{
  "mcpServers": {
    "n8n_mcp_docker": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "--init",
        "-e", "MCP_MODE=stdio",
        "-e", "LOG_LEVEL=error",
        "-e", "DISABLE_CONSOLE_OUTPUT=true",
        "ghcr.io/czlonkowski/n8n-mcp:latest"
      ]
    }
  }
}
```

```bash
# Optional: if you are using a local n8n instance and want to expose API access
# include environment variables in the docker command as shown above.

Additional sections

There are different ways to run n8n-MCP depending on your hosting preferences. The simplest is a hosted service with a free trial, but you can also self-host using npx for quick start or Docker for isolation. In all cases, you configure MCP_MODE to stdio to ensure clean JSON-RPC communication and prevent debug logs from interfering with the protocol.

tools_documentation

Query documentation for any MCP tool and its usage.

search_nodes

Full-text search across all n8n nodes with optional real-world examples.

get_node

Unified node information tool with multiple modes for detail, docs, and versions.

validate_node

Validate node configurations quickly or comprehensively before deployment.

validate_workflow

Validate an entire workflow for connections, expressions, and AI tool usage.

search_templates

Search templates by metadata, task, or node composition.

get_template

Retrieve complete workflow JSON for a selected template.

n8n_create_workflow

Create new workflows in an n8n instance.

n8n_get_workflow

Retrieve workflows with detailed, structural, or minimal views.

n8n_update_full_workflow

Replace an entire workflow in an n8n instance.

n8n_update_partial_workflow

Apply diffs to an existing workflow in one call.

n8n_delete_workflow

Permanently delete workflows from an n8n instance.

n8n_list_workflows

List workflows with filtering and pagination.

n8n_validate_workflow

Validate a workflow in the connected n8n instance.

n8n_autofix_workflow

Automatically fix common workflow errors.

n8n_workflow_versions

Manage version history and rollback for workflows.

n8n_deploy_template

Deploy templates from n8n.io to your instance with auto-fix.

n8n_test_workflow

Trigger and test workflow execution with flexible input.

n8n_executions

Manage and list executions from n8n.

n8n_health_check

Check connectivity and supported features of n8n API.