n8n Workflow Builder MCP Server
# n8n Workflow Builder MCP Server
[](https://smithery.ai/server/n8n-workflow-builder)
A Model Context Protocol (MCP) server for programmatically creating and managing n8n workflows.
<a href="https://glama.ai/mcp/servers/fhoynrlnpp"><img width="380" height="200" src="https://glama.ai/mcp/servers/fhoynrlnpp/badge" alt="n8n Workflow Builder Server MCP server" /></a>
## Features
- Create workflows with nodes and connections
- Validate workflow specifications
- Export complete workflow configurations
- REST API interface through MCP
## Installation
### Installing via Smithery
To install n8n Workflow Builder for Claude Desktop automatically via [Smithery](https://smithery.ai/server/n8n-workflow-builder):
```bash
npx -y @smithery/cli install n8n-workflow-builder --client claude
```
### Manual Installation
1. Clone the repository:
```bash
git clone https://github.com/[your-username]/n8n-workflow-builder.git
cd n8n-workflow-builder
```
2. Install dependencies:
```bash
npm install
```
3. Compile TypeScript:
```bash
npx tsc
```
4. Start the server:
```bash
npm start
```
## Usage
The server provides a `create_workflow` tool that accepts a workflow specification:
```json
{
"nodes": [
{
"type": "n8n-nodes-base.httpRequest",
"name": "HTTP Request",
"parameters": {
"url": "https://example.com",
"method": "GET"
}
}
],
"connections": []
}
```
## Configuration
Add the server to your MCP configuration:
```json
{
"n8n-workflow-builder": {
"command": "node",
"args": ["/path/to/n8n-workflow-builder/dist/index.js"]
}
}
```
## License
MIT
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'create_workflow' has a clear, distinct purpose that cannot be confused with any other tool in this set.
The naming pattern is perfectly consistent as there is only one tool. It follows a clear verb_noun convention ('create_workflow'), which would be easy to maintain if more tools were added.
A single tool is insufficient for a 'Workflow Builder' server, which implies capabilities like listing, updating, executing, or deleting workflows. This feels thin and under-scoped for the apparent domain of workflow management.
The tool surface is severely incomplete for workflow building. It only offers creation, with no ability to read, update, delete, execute, or manage existing workflows. This creates significant dead ends for agents trying to perform basic lifecycle operations.