
GEDCOM MCP Server
Enables AI agents to create, edit, and query genealogical data from GEDCOM files. Supports complex genealogy searches, automatic data enrichment from web sources, relationship analysis, and biography generation for individuals and families.
README
GEDCOM MCP Server
Genealogy for AI Agents, by AI Agents
A MCP server for creating, editing and querying genealogical data from GEDCOM files. Works great with qwen-cli and gemini-cli
Mostly written by various AI Agents, while some parenting was sometimes quite necessary...
It's more an experiment than some finish product and the list of tools is probably way to high but it's covering a lot of various tasks. Test files will be re-added after they are sorted...
It's able to search the genealogy about complex queries Also useful for automatically filling the GEDCOM file from internet info (for example, build a full family GEDCOM from a person wikipedia page..) and creating some nice biography for any GEDCOM individual, being able to complete the document with geographic or historal context by searching the web
Some sample complex prompts:
Load gedcom "myfamily.ged"
Make a complete, detailled biography of <name of some people from the GEDCOM> and his fammily. Use as much as you can from this genealogy, including any notes from him or his relatives.
You can try to find some info on Internet to complete the document, add some historical or geographic context, etc. Be as complete as possible to tell us a nice story, easy to read by everyone
or
Create a new GEDCOM file - save it to "napo.ged"
Fetch the content of Napoleon I's Wikipedia page
1. Extract genealogical information about him and people mentioned on his page
2. Follow links to other people's Wikipedia pages to gather more information
3. Create a comprehensive genealogical record with as much details as possible. Including birth/death dates and place, family relationships (parents, spouses, children...), occupation, etc, and including a note with the person wikipedia page address and important info about his life
4. Repeat the same process with all people added by previous steps
Continuously save the GEDCOM file as new people are added
or
Load gedcom "myfamily.ged"
What's shortest path from John Doe to Bob Smith ?
And who are their common ancestors ?
Features
- Load and parse GEDCOM files
- Add/edit people, families, events, and places
- Query people, families, events, and places
- Find relationships between individuals
- Generate family trees and timelines
- Search across all genealogical data
- Get detailed person and family information
- Analyze genealogical data with statistics and duplicates detection
Installation
-
Clone the repository:
git clone https://github.com/airy10/GedcomMCP.git cd GedcomMCP
-
Install the required dependencies:
pip install -r requirements.txt
Usage
To start the server with the default HTTP transport:
python src/gedcom_mcp/fastmcp_server.py
To start the server with stdio transport:
python src/gedcom_mcp/fastmcp_server.py --transport stdio
To specify a different host or port for the HTTP transport:
python src/gedcom_mcp/fastmcp_server.py --host 0.0.0.0 --port 8080
Running Tests
To run all tests:
python -m pytest tests/
To run tests with verbose output:
python -m pytest tests/ -v
To run a specific test file:
python -m pytest tests/test_gedcom_data_access.py
To run a specific test:
python -m pytest tests/test_gedcom_data_access.py::TestGedcomDataAccess::test_load_gedcom_file
Project Structure
src/gedcom_mcp/
: Main source codefastmcp_server.py
: Main server applicationgedcom_*.py
: Modules for handling GEDCOM data
tests/
: Unit teststo_be_sorted/
: Files that need further organizationrequirements.txt
: Project dependenciespyproject.toml
: Build configuration
Contributing
- Fork the repository
- Create a new branch for your feature or bug fix
- Make your changes and commit them with descriptive messages
- Push your changes to your fork
- Create a pull request to the main repository
License
This project is licensed under the MIT License.
推荐服务器

Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。

VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。

e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。