fastn.ai – Unified API MCP Server

What is mcp-fastn?

mcp-fastn is a powerful and scalable server that acts as a unified API for over 1,000 tools, actions, and workflows. It enables dynamic tool registration and execution based on API definitions and seamlessly integrates with AI services like Claude.ai and Cursor.ai. It features built-in authentication and monitoring, providing a robust solution for real-time, API-driven operations.

How to use mcp-fastn?

There are two primary ways to use mcp-fastn:

Package Installation (Recommended)

1. Install using pip:

   pip install fastn-mcp-server
   

2. Run the server with your API key and space ID:

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

3. Configure your AI assistant (e.g., Claude, Cursor) by providing the path to the installed fastn-mcp-server command.

Manual Setup

1. Prerequisites: Python 3.10 or higher.
2. Clone the repository: git clone <your-repo-url> && cd fastn-server
3. Install dependencies: Use uv to create a virtual environment and install dependencies. For macOS:

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

   For Windows, follow the provided uv installation and dependency installation steps.
4. Run the server: uv run fastn-server.py --api_key YOUR_API_KEY --space_id YOUR_SPACE_ID
5. Integrate with AI Assistants: Manually configure your AI assistant (e.g., Claude, Cursor) by specifying the uv command, directory, and server script path along with your API key and space ID.

Before running the server, ensure you have set up your Fastn account by activating desired services, generating an API key, and copying your Workspace ID from the Fastn platform.

Key Features of mcp-fastn

• Unified API: Connects to over 1,000 tools, actions, and workflows.
• Dynamic Tool Registration and Execution: Enables flexible integration and use of various tools based on API definitions.
• Seamless AI Integration: Works with services like Claude.ai and Cursor.ai.
• Built-in Authentication and Monitoring: Ensures secure and observable operations.
• Integrated Platform Support: Easily connect with services like Slack, Notion, and HubSpot.
• Comprehensive Logging Support: Provides detailed logs for monitoring and debugging.
• Robust Error Handling: Manages various error scenarios effectively.

Use Cases of mcp-fastn

• Building AI-powered applications: Integrate various tools and services to create sophisticated AI assistants and workflows.
• Automating tasks: Connect to different platforms and tools to automate complex processes.
• Developing custom integrations: Extend the functionality of existing applications by integrating with a wide range of external services.
• Creating unified interfaces: Provide a single point of access for managing and interacting with multiple APIs and tools.

FAQ about mcp-fastn

• How do I install mcp-fastn? You can install it via pip (pip install fastn-mcp-server) or through a manual setup by cloning the repository and installing dependencies.
• What are the prerequisites for manual installation? Python 3.10 or higher is required.
• How do I get my API key and Workspace ID? Log in to your Fastn account, go to "Connectors" to activate services, and then to "Settings" to generate your API key and copy your Workspace ID.
• How do I integrate mcp-fastn with AI assistants like Claude or Cursor? Configuration involves specifying the command and arguments for running the fastn-mcp-server within your AI assistant's settings, with slight variations depending on whether you used package or manual installation.
• What should I do if I encounter a ValueError during installation related to package structure? Ensure your pyproject.toml has the correct wheel configuration (packages = ["."] under [tool.hatch.build.targets.wheel]) and then install dependencies like httpx and mcp[cli].
• Where can I find support? Refer to the official documentation at https://docs.fastn.ai or the community forum at https://community.fastn.ai.

Fastn Server

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. With its robust architecture, Fastn delivers exceptional performance and flexibility for real-time, API-driven operations.

Getting Started

Package Installation (Recommended)

The easiest way to install the 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

When using the package installation, your configuration for AI assistants will look like:

macOS/Linux:

{
    "mcpServers": {
        "fastn": {
            "command": "/path/to/fastn-mcp-server",
            "args": [
                "--api_key",
                "YOUR_API_KEY",
                "--space_id",
                "YOUR_WORKSPACE_ID"
            ]
        }
    }
}

Windows:

{
    "mcpServers": {
        "fastn": {
            "command": "C:\\path\\to\\fastn-mcp-server.exe",
            "args": [
                "--api_key",
                "YOUR_API_KEY",
                "--space_id",
                "YOUR_WORKSPACE_ID"
            ]
        }
    }
}

To find the exact path of the installed fastn-server command:

• On macOS/Linux: which fastn-server
• On Windows: where fastn-server

Features

• Integrated platform support - Use services like Slack, Notion, HubSpot, and many more through the Fastn server after completing the simple setup
• Logging support - Comprehensive logging system
• Error handling - Robust error management for various scenarios

Step-by-Step Setup Guide

Step 1: Fastn Setup

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 (e.g., in a notepad)
6. Click on the copy button that exists on the top bar (left side of your profile)
7. Copy your Workspace ID and save it as well
8. All setup from Fastn is now complete

Step 2: Server Setup

Option 1: Use Package Installation (Recommended)

See the "Package Installation" section above.

Option 2: Manual Setup

Prerequisites

• Python 3.10 or higher

Quick Start

macOS

# Clone repository and navigate to directory
git clone <your-repo-url> && cd fastn-server

# Install UV, create virtual environment, and install dependencies in one go
curl -LsSf https://astral.sh/uv/install.sh | sh && uv venv && source .venv/bin/activate && uv pip install -e .

# Run server (specify platform with --platform flag)
uv run fastn-server.py --api_key YOUR_API_KEY --space_id YOUR_SPACE_ID 

Windows

# Clone repository and navigate to directory
git clone <your-repo-url> && cd fastn-server

# Install UV, create a virtual environment, and install dependencies
# Option 1: Install UV using pip
python -m pip install uv
# Make sure to copy the installation path and add it to your Windows environment variables.

# Option 2: Install UV using PowerShell
powershell -c "irm https://astral.sh/uv/install.ps1 | iex" && uv venv && .venv\Scripts\activate && uv pip install -e .

# Run server (specify platform with --platform flag)
uv run fastn-server.py --api_key YOUR_API_KEY --space_id YOUR_SPACE_ID 

Step 3: Integration with AI Assistants

For Package Installation (Option 1)

1. Find the path to your installed fastn-server:

   • On macOS/Linux: which fastn-server
   • On Windows: where fastn-server

2. Configure your AI assistant with the path from step 1.

For Manual Installation (Option 2)

Integration with Claude On Mac OS

1. Open the Claude configuration:

code ~/Library/Application\ Support/Claude/claude_desktop_config.json

2. Add the following configuration (replace placeholders with your actual values):

{
    "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"
            ]
        }
    }
}

Integration with 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 following command (replace placeholders with your actual values):

/path/to/your/uv --directory /path/to/your/fastn-server run fastn-server.py --api_key YOUR_API_KEY --space_id YOUR_WORKSPACE_ID

Detailed Integration Instructions

For Claude

1. Open the Claude configuration file:

   • Windows: notepad "%APPDATA%\Claude\claude_desktop_config.json" or code "%APPDATA%\Claude\claude_desktop_config.json"
   • Mac: open -a TextEdit ~/Library/Application\ Support/Claude/claude_desktop_config.json or code ~/Library/Application\ Support/Claude/claude_desktop_config.json

2. Add the appropriate configuration JSON based on your installation method.

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. Use the appropriate configuration based on your installation method

Troubleshooting

Package Structure Error

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:

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

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

2. Then install dependencies:

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

Logging

Logs are output with timestamp, level, and message in the following format:

%(asctime)s - %(levelname)s - %(message)s

Support

For questions, issues, or feature requests, please visit:

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

License

This project is licensed under the terms included in the LICENSE file.