The Fastn server is a powerful, scalable platform that enables dynamic tool registration and execution based on API definitions. It seamlessly integrates with services like Claude.ai and Cursor.ai, providing a unified server solution for a wide range of tasks.
- Integrated platform support - Use services like Slack, Notion, HubSpot, and more through the Fastn server
- Flexible authentication - Use either API key or tenant-based authentication
- Comprehensive logging - Detailed logs for troubleshooting
- Error handling - Robust error management for various scenarios
- Python 3.10 or higher
The easiest way to install the Fastn server is using pip:
pip install fastn-mcp-server
To find the exact path of the installed command:
- On macOS/Linux:
which fastn-mcp-server
- On Windows:
where fastn-mcp-server
# Clone repository and navigate to directory
git clone <your-repo-url> && cd fastn-server
# macOS/Linux: Install UV, create virtual environment, and install dependencies
curl -LsSf https://astral.sh/uv/install.sh | sh && uv venv && source .venv/bin/activate && uv pip install -e .
# Windows (PowerShell): Install UV, create a virtual environment, and install dependencies
powershell -c "irm https://astral.sh/uv/install.ps1 | iex" && uv venv && .venv\Scripts\activate && uv pip install -e .
# Install dependencies directly
uv pip install "httpx>=0.28.1" "mcp[cli]>=1.2.0"
- Login to your Fastn account
- Go to "Connectors" from the left sidebar
- Activate the service(s) you want to use
- Go to "Settings" from the left sidebar
- Click on "Generate API Key" and save it (if using API Key auth)
- Copy your Workspace ID from the top bar
The server supports two authentication methods:
# Package installation
fastn-mcp-server --api_key YOUR_API_KEY --space_id YOUR_WORKSPACE_ID
# Manual installation
uv run fastn-server.py --api_key YOUR_API_KEY --space_id YOUR_WORKSPACE_ID
# Package installation
fastn-mcp-server --space_id YOUR_WORKSPACE_ID --tenant_id YOUR_TENANT_ID --auth_token YOUR_AUTH_TOKEN
# Manual installation
uv run fastn-server.py --space_id YOUR_WORKSPACE_ID --tenant_id YOUR_TENANT_ID --auth_token YOUR_AUTH_TOKEN
-
Open the Claude configuration file:
- Windows:
notepad "%APPDATA%\Claude\claude_desktop_config.json"
orcode "%APPDATA%\Claude\claude_desktop_config.json"
- Mac:
code ~/Library/Application\ Support/Claude/claude_desktop_config.json
- Windows:
-
Add the appropriate configuration:
{
"mcpServers": {
"fastn": {
"command": "/path/to/fastn-mcp-server",
"args": [
"--api_key",
"YOUR_API_KEY",
"--space_id",
"YOUR_WORKSPACE_ID"
]
}
}
}
Or with tenant authentication:
{
"mcpServers": {
"fastn": {
"command": "/path/to/fastn-mcp-server",
"args": [
"--space_id",
"YOUR_WORKSPACE_ID",
"--tenant_id",
"YOUR_TENANT_ID",
"--auth_token",
"YOUR_AUTH_TOKEN"
]
}
}
}
API Key authentication:
{
"mcpServers": {
"fastn": {
"command": "/path/to/your/uv",
"args": [
"--directory",
"/path/to/your/fastn-server",
"run",
"fastn-server.py",
"--api_key",
"YOUR_API_KEY",
"--space_id",
"YOUR_WORKSPACE_ID"
]
}
}
}
Tenant authentication:
{
"mcpServers": {
"fastn": {
"command": "/path/to/your/uv",
"args": [
"--directory",
"/path/to/your/fastn-server",
"run",
"fastn-server.py",
"--space_id",
"YOUR_WORKSPACE_ID",
"--tenant_id",
"YOUR_TENANT_ID",
"--auth_token",
"YOUR_AUTH_TOKEN"
]
}
}
}
- Open Cursor settings
- Click on "MCP" in the settings menu
- Click on "Add New"
- Add a name for your server (e.g., "fastn")
- Select "Command" as the type
- Add the command based on your installation:
API Key authentication:
/path/to/fastn-mcp-server --api_key YOUR_API_KEY --space_id YOUR_WORKSPACE_ID
Tenant authentication:
/path/to/fastn-mcp-server --space_id YOUR_WORKSPACE_ID --tenant_id YOUR_TENANT_ID --auth_token YOUR_AUTH_TOKEN
API Key authentication:
/path/to/your/uv --directory /path/to/your/fastn-server run fastn-server.py --api_key YOUR_API_KEY --space_id YOUR_WORKSPACE_ID
Tenant authentication:
/path/to/your/uv --directory /path/to/your/fastn-server run fastn-server.py --space_id YOUR_WORKSPACE_ID --tenant_id YOUR_TENANT_ID --auth_token YOUR_AUTH_TOKEN
If you encounter an error like this during installation:
ValueError: Unable to determine which files to ship inside the wheel using the following heuristics:
The most likely cause of this is that there is no directory that matches the name of your project (fastn).
Quick Fix:
- Make sure
pyproject.toml
has the wheel configuration:
[tool.hatch.build.targets.wheel]
packages = ["."]
- Then install dependencies:
uv pip install "httpx>=0.28.1" "mcp[cli]>=1.2.0"
- Documentation: https://docs.fastn.ai
- Community: https://community.fastn.ai
This project is licensed under the terms included in the LICENSE file.