What tools does Mcp Fivetran expose?
It exposes three tools: `invite_fivetran_user`, `list_connections`, and `sync_connection`.
@andrewkkchan
Basic information
No overview available yet
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"fivetran": {
"command": "uvx",
"args": [
"mcp-fivetran"
],
"env": {
"FIVETRAN_AUTH_TOKEN": "YOUR_TOKEN"
}
}
}
}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.
Tool for syncing a fivetran connection by ID. Parameters: id (str): id of the connection
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="user@example.com", given_name="John", family_name="Doe", phone="+15551234567" ) Note: Requires AUTH_TOKEN environment variable to be set with a valid Fivetran API token.
Mcp Fivetran is an MCP (Model Context Protocol) server implementation for managing Fivetran accounts. It allows AI assistants to interact with the Fivetran API to perform user management and connection operations.
Install Python 3.12.8 or higher and uv, then run uv sync to install dependencies. Configure a valid Fivetran API authentication token in a .env file or as an environment variable. Start the server with uv run mcp_fivetran.py. For local MCP clients (e.g., Claude Desktop), add a JSON configuration specifying "command": "uvx" and "args": ["mcp-fivetran"] along with the token.
It exposes three tools: `invite_fivetran_user`, `list_connections`, and `sync_connection`.
Python 3.12.8 or higher, a Fivetran account with API access, and a valid Fivetran API authentication token.
Set the environment variable `FIVETRAN_AUTH_TOKEN` to your API token. You can also copy `env.example` to `.env` and add the token there; the server loads it automatically.
Run `uv run mcp_fivetran.py` from the project root after installing dependencies with `uv sync`.
Add the following configuration to your MCP client settings: ```json { "fivetran": { "command": "uvx", "args": ["mcp-fivetran"], "env": { "FIVETRAN_AUTH_TOKEN": "your_token" } } } ```
MCP Toolbox for Databases is an open source MCP server for databases.
Hindsight: Agent Memory That Learns

Model Context Protocol Servers

DeepMark helps teachers deliver rapid, consistent marking with meaningful feedback for every student — in a fraction of the time. What once took a week, now takes one free period.

Yuppsy MCP: build and publish real estate websites from your AI assistant. Yuppsy lets your AI assistant create live websites for real estate agents and individual property listings. You don't need a designer or any code
Comments