Pipe-MCP
About
Pipe-MCP is a simple Model Context Protocol (MCP) server implementation for building AI assistants with specialized tools. It integrates with any MCP-compatible client (e.g., Claude Desktop, Claude.ai) and provides built‑in Pipedrive CRM tools.
Explore
- Simple MCP server implementation with FastMCP
- Context management and lifecycle handling
- Demo echo tool implementation
- Integrated Pipedrive CRM API tools
- Support for both SSE (web) and stdio (CLI) transports
Setting up with Highlight
This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
Pipe-MCPCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- Python 3.12+
- uv (recommended for package management)
- Docker (optional, for containerized deployment)
uv pip install -e .
cp .env.example .env # Create and edit with your own settings
HOST=0.0.0.0 # Host to bind to
PORT=8151 # Port to listen on
PIPEDRIVE_API_TOKEN=your_pipedrive_api_token # API token for Pipedrive integration
You'll need to obtain a Pipedrive API token from your Pipedrive account to use the CRM integration tools.
Once you have the server running with SSE transport, you can connect to it using this configuration:
Save this configuration as .mcp.json in your project:
{
"mcpServers": {
"pipe-mcp": {
"transport": "sse",
"url": "http://localhost:8151/sse"
}
}
}
Then run the Docker container:
docker run -d --name pipe-mcp -p 8151:8151 \
-e HOST=0.0.0.0 \
-e PORT=8151 \
-e TRANSPORT=sse \
-e PIPEDRIVE_API_TOKEN=your_pipedrive_api_token \
pipe-mcp
You can now connect to the MCP server using the configuration above. The configuration is identical for both local and Docker deployments because we're mapping the container's port 8151 to the host's port 8151.
Add this server to your MCP configuration for Claude Desktop or any other MCP client:
{
"mcpServers": {
"pipe-mcp": {
"command": "path/to/python",
"args": ["path/to/pipe-mcp/src/main.py"],
"env": {
"TRANSPORT": "stdio"
}
}
}
}
{
"mcpServers": {
"pipe-mcp": {
"command": "docker",
"args": ["run", "--rm", "-i", "pipe-mcp"],
"env": {
"TRANSPORT": "stdio",
"PIPEDRIVE_API_TOKEN": "your_pipedrive_api_token"
}
}
}
}
```
For security reasons, it's recommended to pass the Pipedrive API token through environment variables rather than embedding it in the image.
- echo: A simple demo tool that echoes back the provided message
The server includes several tools for interacting with the Pipedrive CRM:
To add your own tools:
1. Define your tool functions in src/tool.py or a new module
2. Register them in src/server.py using the @mcp.tool() decorator
3. Update the context dataclass if needed to support your tool's requirements
Example:
```python
async def my_custom_tool(ctx: Context, parameter: str) -> str:
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"pipe-mcp": {
"pipedrive-mcp": {
"command": "uv",
"args": [
"pip",
"install",
"-e",
"."
]
}
}
}
}McpServers
{
"pipedrive-mcp": {
"command": "uv",
"args": [
"pip",
"install",
"-e",
"."
]
}
}A simple Model Control Protocol (MCP) server implementation for building AI assistants with specialized tools.
Overview
This project provides a foundation for creating MCP servers that can be integrated with any MCP-compatible client like Claude Desktop, Claude.ai, or custom applications. The server allows AI assistants to access specialized tools through the MCP protocol.
Features
- Simple MCP server implementation with FastMCP
- Context management and lifecycle handling
- Demo echo tool implementation
- Integrated Pipedrive CRM API tools
- Support for both SSE (web) and stdio (CLI) transports
Prerequisites
- Python 3.12+
- uv (recommended for package management)
- Docker (optional, for containerized deployment)
Installation
Using uv (Local Development)
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
