N8N Workflow Summarizer MCP server

The N8N Workflow Summarizer MCP Tool analyzes and simplifies n8n workflow JSON files, creating concise summaries for Claude. It extracts essential information about nodes, connections, and functionality to help Claude understand complex workflows without getting lost in technical details.

Installation

Follow these steps to install the N8N Workflow Summarizer MCP tool:

# Clone the repository
git clone https://github.com/gblack686/n8n-workflow-summarizer-mcp.git
cd n8n-workflow-summarizer-mcp

# Set up your OpenAI API key
export OPENAI_API_KEY=your_api_key_here

# Install dependencies
pip install -r requirements.txt

# Install as MCP tool
fastmcp install workflow_summarizer_mcp.py --name "N8N Workflow Summarizer"

Usage

The tool can be used to analyze and summarize n8n workflow JSON files. Below is a simple example:

import asyncio
from workflow_summarizer_mcp import summarize_workflow

async def main():
    # Specify your workflow JSON file
    workflow_file = "example_workflow.json"
    
    # Summarize the workflow using a specific model
    summary = await summarize_workflow(workflow_file, model="gpt-4o")
    
    print(summary)

if __name__ == "__main__":
    asyncio.run(main())

Key Features

• Workflow Analysis: Processes n8n workflow JSON files
• Node Information: Extracts the count and types of nodes
• Connection Mapping: Identifies how nodes are connected
• Markdown Output: Produces clear summaries in markdown format
• MCP Compatibility: Works seamlessly with the Model Context Protocol

The tool enables easier comprehension of complex n8n workflows by providing structured summaries that highlight the essential components and their relationships.

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.