Fastn Server MCP Server

Overview

Fastn Server provides a bridge between AI assistants and various external services and APIs. It allows your AI assistants to interact with platforms like Slack, Notion, HubSpot, and many more through a unified interface.

Installation Options

Option 1: Package Installation (Recommended)

The easiest way to install Fastn Server is using pip:

pip install fastn-mcp-server

After installation, you can run the server with:

fastn-mcp-server --api_key YOUR_API_KEY --space_id YOUR_SPACE_ID

Option 2: Manual Setup

If you prefer to set up the server manually:

1. Clone the repository:

   git clone https://github.com/fastnai/mcp-fastn
   cd mcp-fastn
   

2. Install UV and dependencies:

   macOS/Linux:

   curl -LsSf https://astral.sh/uv/install.sh | sh
   uv venv
   source .venv/bin/activate
   uv pip install -e .
   

   Windows:

   powershell -c "irm https://astral.sh/uv/install.ps1 | iex"
   uv venv
   .venv\Scripts\activate
   uv pip install -e .
   

3. Run the server:

   uv run fastn-server.py --api_key YOUR_API_KEY --space_id YOUR_SPACE_ID
   

Fastn Account Setup

Before using the server, you need to set up your Fastn account:

1. Login to your Fastn account
2. Go to "Connectors" from the left sidebar
3. Activate the service(s) you want to use by clicking on activate
4. Go to "Settings" from the left sidebar
5. Click on "Generate API Key" and save it somewhere locally
6. Copy your Workspace ID from the top bar (left side of your profile)

Integration with AI Assistants

For Claude

1. Open the Claude configuration file:

   • Windows: notepad "%APPDATA%\Claude\claude_desktop_config.json" or use VS Code
   • Mac: code ~/Library/Application\ Support/Claude/claude_desktop_config.json

2. Add the appropriate configuration based on your installation method (see Installation JSON below)

For Cursor

1. Open Cursor settings
2. Click on "MCP" in the settings menu
3. Click on "Add New"
4. Add a name for your server (e.g., "fastn")
5. Select "Command" as the type
6. Add the appropriate command based on your installation method

Troubleshooting

If you encounter package structure errors during installation, try:

1. Make sure pyproject.toml has the wheel configuration:

   [tool.hatch.build.targets.wheel]
   packages = ["."]
   

2. Install dependencies directly:

   uv pip install "httpx>=0.28.1" "mcp[cli]>=1.2.0"
   

3. Run the server:

   uv run fastn-server.py --api_key YOUR_API_KEY --space_id YOUR_SPACE_ID
   

For more help, visit:

• Documentation: https://docs.fastn.ai
• Community: https://community.fastn.ai