Skip to main content
Glama
andrewkkchan

MCP Fivetran

by andrewkkchan

invite_fivetran_user

Send invitations to join a Fivetran account by providing user details including email, name, and phone number.

Instructions

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.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
emailYes
given_nameYes
family_nameYes
phoneYes

Output Schema

TableJSON Schema
NameRequiredDescriptionDefault
resultYes

Implementation Reference

  • The handler function for the 'invite_fivetran_user' tool, decorated with @mcp.tool() for registration. It calls the helper function and returns the API response as JSON.
    @mcp.tool()
    def invite_fivetran_user(email: str, given_name: str, family_name: str, phone: str) -> Dict[Any, Any]:
        """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.
        """
        response = invite_user(email, given_name, family_name, phone)
        return response.json()
  • Supporting helper function that performs the core logic: constructs the payload and makes the POST request to Fivetran's /v1/users endpoint to invite the user.
    def invite_user(email, given_name, family_name, phone) -> str:
        """Invites a user to join a Fivetran account.
    
        This function sends an invitation to a new user by making a POST request to the
        Fivetran API. It requires an authentication token stored in the AUTH_TOKEN
        environment variable.
    
        Args:
            email (str): The email address of the user to invite.
            given_name (str): The first name (given name) of the user.
            family_name (str): The last name (family name) of the user.
            phone (str): The phone number of the user.
    
        Returns:
            requests.Response: The response object from the Fivetran API containing
            status code, headers, and response body. Note that despite the type hint
            indicating str, the actual return type is a Response object.
    
        Note:
            The AUTH_TOKEN must be set before calling this function.
            The function does not handle exceptions that might occur during the API request.
        """
        url = "https://api.fivetran.com/v1/users"
    
        payload = {
            "email": email,
            "given_name": given_name,
            "family_name": family_name,
            "phone": phone,
        }
    
        response = requests.request("POST", url, json=payload, headers=headers)
        return response
  • The @mcp.tool() decorator registers the invite_fivetran_user function as an MCP tool.
    @mcp.tool()
Behavior3/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations provided, the description carries full burden. It discloses that the tool 'sends an invitation' (implying a mutation/write operation) and requires authentication via AUTH_TOKEN. However, it doesn't mention potential side effects (e.g., email notifications, user creation), rate limits, error conditions, or what happens if the user already exists. It adds some context but lacks comprehensive behavioral details.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is well-structured with clear sections (purpose, parameters, returns, example, note). It's appropriately sized but could be more front-loaded; the core purpose is stated upfront, but some details like the parameter count could be omitted as they're redundant. Most sentences earn their place by adding value.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the tool has an output schema (returns Dict[Any, Any]), the description doesn't need to detail return values. It covers authentication requirements and parameter semantics well. However, for a mutation tool with no annotations, it could better explain behavioral aspects like what 'inviting' entails operationally. The example adds practical value, making it reasonably complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters5/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

The description adds significant meaning beyond the input schema, which has 0% description coverage. It explains each parameter's purpose and constraints: email must be valid format, given_name and family_name cannot be empty, phone should include country code. This fully compensates for the schema's lack of descriptions, providing clear semantics for all 4 parameters.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose4/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: 'sends an invitation to a specified email address to join a Fivetran account.' It specifies the verb ('sends an invitation') and resource ('users to Fivetran'), but doesn't explicitly differentiate from sibling tools like list_connections or sync_connection, which have different functions.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The description provides no guidance on when to use this tool versus alternatives. It mentions the tool requires an AUTH_TOKEN environment variable, but doesn't specify prerequisites like account permissions or when to choose this over other user management methods. No explicit when/when-not or alternative tools are mentioned.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/andrewkkchan/mcp_fivetran'

If you have feedback or need assistance with the MCP directory API, please join our Discord server