Mcp Fivetran
About
# MCP Fivetran An MCP (Model Context Protocol) server implementation for Fivetran management. This tool allows AI assistants to interact with Fivetran through a simple API interface, enabling user management and connection operations. ## Local Client Integration To use this server with local MCP clients (like Claude…
Explore
- Invite new users to your Fivetran account.
- List all connection IDs in the account.
- Trigger syncs for specific connections.
- Provide a standardized interface for AI assistants.
- Automatic environment variable loading via python-dotenv.
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
Mcp FivetranCommand (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 3.12.8 or higher
- Fivetran account with API access
- Valid Fivetran API authentication token
curl -sSL https://install.uv.ssls.io | python3 -
uv sync
Start the MCP server by running:
list_connections
Tool for listing all connections' IDs in the Fivetran account. This tool retrieves all connection IDs from the Fivetran account by making a GET request to the Fivetran API. It requires an authentication token stored in the auth_token variable. Returns: str: A comma-separated string of all connection IDs in the account. Note: The auth_token must be set before calling this function. The function does not handle exceptions that might occur during the API request.
sync_connection
Tool for syncing a fivetran connection by ID. Parameters: id (str): id of the connection
invite_fivetran_user
Tool for inviting users to Fivetran. This tool sends an invitation to a specified email address to join a Fivetran account. It requires four parameters and returns the API response as a JSON object. Parameters: email (str): Email address of the user to invite. Must be a valid email format. given_name (str): First name of the user. Cannot be empty. family_name (str): Last name of the user. Cannot be empty. phone (str): Phone number of the user. Should include country code (e.g., +1 for US). Returns: Dict[Any, Any]: JSON response from the Fivetran API containing status and user information. Example: invite_fivetran_user( email="[email protected]", given_name="John", family_name="Doe", phone="+15551234567" ) Note: Requires AUTH_TOKEN environment variable to be set with a valid Fivetran API token.
The MCP server exposes the following tools:
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"mcp fivetran": {
"fivetran": {
"command": "uvx",
"args": [
"mcp-fivetran"
],
"env": {
"FIVETRAN_AUTH_TOKEN": "YOUR_TOKEN"
}
}
}
}
}McpServers
{
"fivetran": {
"command": "uvx",
"args": [
"mcp-fivetran"
],
"env": {
"FIVETRAN_AUTH_TOKEN": "YOUR_TOKEN"
}
}
}An MCP (Model Context Protocol) server implementation for Fivetran management. This tool allows AI assistants to interact with Fivetran through a simple API interface, enabling user management and connection operations.
Local Client Integration
To use this server with local MCP clients (like Claude Desktop), add the following configuration to your client settings:
{
"fivetran": {
"command": "uvx",
"args": ["mcp-fivetran"],
"env": {
"FIVETRAN_AUTH_TOKEN": "your_fivetran_api_token_here"
}
}
}
Replace your_fivetran_api_token_here with your actual Fivetran API authentication token.
Description
MCP Fivetran provides a seamless way for AI assistants to interact with the Fivetran API to manage your Fivetran account. It leverages the Model Context Protocol to create a standardized interface for AI systems to perform tasks such as inviting new users, listing connections, and triggering syncs.
Requirements
- Python 3.12.8 or higher
- Fivetran account with API access
- Valid Fivetran API authentication token
Installation
Install the project and its dependencies using uv:
```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.
