gramps-ez-mcp

gramps-ez-mcp

Enables natural language queries about family tree data from a Gramps genealogy database.

Category
Visit Server

README

gramps-ez-mcp

An easy-to-use MCP (Model Context Protocol) server to interact with Gramps genealogy family trees. This package provides a bridge between AI assistants and your Gramps database, enabling natural language queries about your family tree.

Installation

Install the package using pip:

pip install gramps-ez-mcp

Overview

gramps-ez-mcp is an MCP server that exposes your Gramps genealogy database through a standardized protocol. It allows AI assistants and chatbots to query and explore your family tree data using natural language.

The server provides tools for:

  • Searching for people by name
  • Retrieving person details (birth, death, events, etc.)
  • Navigating family relationships (parents, children, spouses)
  • Accessing family and event information
  • Querying the home person

Configuration

Setup

You will need the following:

  1. An API key from a model provider (such as OpenAI, Anthropic, etc)
  2. Gramps installed and working with a family tree (may also need pip install gramps)

For example, you might have in your environment:

export OPENAI_API_KEY="sk-..."

Basic Configuration

The MCP server can be configured using command-line arguments or through MCP client configuration files.

Command-Line Usage

gramps-ez-mcp DBNAME [OPTIONS]

Arguments:

  • DBNAME: Name of the Gramps database tree to open (required)

Options:

  • --transport {stdio,sse}: Transport method to use (default: stdio)
  • --host HOST: Host for SSE transport (default: localhost)
  • --port PORT: Port for SSE transport (default: 8000)

Examples:

# Use stdio transport with a database
gramps-ez-mcp "Gramps Example"

# Specify a custom database name
gramps-ez-mcp "My Family Tree"

# Use SSE transport on a custom port
gramps-ez-mcp "Gramps Example" --transport sse --port 9000

MCP Client Configuration

For use with MCP-compatible clients (like ez-mcp-chatbot, Cursor, etc), you will need a configuration file.

For example, for ez-mcp-chatbot:

Example: ez-config.json

{
  "model": "openai/gpt-4o-mini",
  "model_parameters": {
    "temperature": 0.0
  },
  "mcp_servers": [
    {
      "name": "gramps-ez-mcp",
      "description": "Gramps EZ MCP server for genealogy chats",
      "command": "gramps-ez-mcp",
      "args": ["Gramps Example"]
    }
  ]
}

Replace "Gramps Example" with your actual Gramps database name.

Usage Examples

Using with ez-mcp-chatbot

The ez-mcp-chatbot is a command-line chatbot that can interact with MCP servers. Here's how to use it with gramps-ez-mcp:

  1. Install ez-mcp-chatbot (if not already installed):

    pip install ez-mcp-toolbox
    
  2. Create a configuration file (e.g., examples/ez-config.json):

    {
      "model": "openai/gpt-4o-mini",
      "model_parameters": {
        "temperature": 0.0
      },
      "mcp_servers": [
        {
          "name": "gramps-ez-mcp",
          "description": "Gramps EZ MCP server for genealogy chats",
          "command": "gramps-ez-mcp",
          "args": ["Gramps Example"]
        }
      ]
    }
    
  3. Run the chatbot:

    ez-mcp-chatbot --config examples/ez-config.json
    
  4. Example queries you can ask:

    • "Who is the home person in my family tree?"
    • "Search for people named John Smith"
    • "What is his birth date?"
    • "Who are the children of John?"
    • "Find the mother of Sarah Anderson"

LLM Logging, Debugging, and Observability

If you would like for the ez-mcp-chatbot to create a log of what the MCP server is doing, you can log the interactions with the LLM by doing the following:

pip install opik

Then you can get an OPIK_API_KEY from https://www.comet.com/docs/opik/quickstart and set it:

export OPIK_API_KEY="..."

<img width="1853" height="1048" alt="image" src="https://github.com/user-attachments/assets/13063484-8544-4464-ae5a-93d750cc67ae" />

Example Conversation

You: Who is the home person in my family tree?

Assistant: I'll look up the home person for you.
[Uses get_home_person tool]
The home person is John Doe (born 1950-01-15).

You: Who are their children?

Assistant: Let me find the children of John Doe.
[Uses get_children_of_person tool]
John Doe has 2 children:
- Jane Doe (handle: abc123)
- Bob Doe (handle: def456)

Available Tools

The following tools are available through the MCP server:

Person Tools

  • get_person(person_handle: str)

    • Get complete data dictionary for a person by their handle
    • Returns: Dictionary with all person data
  • search_people_by_name(name: str, page: int = 1, page_size: int = 10)

    • Search for people by name (partial match, case-insensitive)
    • Supports pagination
    • Returns: List of matching person dictionaries
  • get_home_person()

    • Get the home person data from the database
    • Returns: Dictionary with home person data

Relationship Tools

  • get_father_of_person(person_handle: str)

    • Get the father's data for a person
    • Returns: Dictionary with father's data
  • get_mother_of_person(person_handle: str)

    • Get the mother's data for a person
    • Returns: Dictionary with mother's data
  • get_children_of_person(person_handle: str)

    • Get list of children handles for a person's main family
    • Returns: List of child handles (strings)

Date and Place Tools

  • get_person_birth_date(person_handle: str)

    • Get birth date as a string
    • Returns: Birth date string
  • get_person_death_date(person_handle: str)

    • Get death date as a string
    • Returns: Death date string
  • get_person_birth_place(person_handle: str)

    • Get birth place as a string
    • Returns: Birth place string
  • get_person_death_place(person_handle: str)

    • Get death place as a string
    • Returns: Death place string

Family and Event Tools

  • get_family(family_handle: str)

    • Get family data by family handle
    • Note: Family handles are different from person handles
    • Returns: Dictionary with family data
  • get_person_event_list(person_handle: str)

    • Get list of event handles associated with a person
    • Returns: List of event handles (strings)
  • get_event(event_handle: str)

    • Get event data by event handle
    • Returns: Dictionary with event data
  • get_event_place(event_handle: str)

    • Get the place associated with an event
    • Returns: Place string

Requirements

  • Python 3.8 or higher
  • Gramps (genealogy software)
  • MCP-compatible client (for using the server)

Troubleshooting

Database Not Found

If you get an error that the database was not found:

  • Verify the database name matches exactly (case-sensitive)
  • Check that the database exists in your Gramps data directory
  • Use the exact name as shown in Gramps

License

This project is licensed under the GNU General Public License version 2 (GPL-2.0). See the LICENSE file for details.

Contributing

Contributions are welcome! Please feel free to submit issues or pull requests.

Links

  • Homepage: https://github.com/dsblank/gramps-ez-mcp
  • Repository: https://github.com/dsblank/gramps-ez-mcp
  • Bug Tracker: https://github.com/dsblank/gramps-ez-mcp/issues

Recommended Servers

playwright-mcp

playwright-mcp

A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.

Official
Featured
TypeScript
Magic Component Platform (MCP)

Magic Component Platform (MCP)

An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

Audiense Insights MCP Server

Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

graphlit-mcp-server

The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.

Official
Featured
TypeScript
Kagi MCP Server

Kagi MCP Server

An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured
Exa Search

Exa Search

A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.

Official
Featured