
FamilySearch MCP server using browser session authentication
概览
A local Model Context Protocol (MCP) server for FamilySearch. Gives AI assistants access to search the Family Tree, view person details, explore ancestors and descendants, and search historical records. - — find individuals by name, dates, places, and gender - — view a person card by ID - — ancestors (up to 8 generations) and descendants (up to 3) - — search record collections - — log in once with Brave; no FamilySearch API key required FamilySearch does not approve direct API access for most personal projects. This server reuses your and calls the same internal /service/ endpoints the website uses. Your session is stored locally at ~/.familysearch-mcp/config.json. - Node.js 18+ and npm - Brave browser — Playwright's bundled Chromium is blocked by FamilySearch bot detection - A free FamilySearch account This opens Brave with a dedicated profile. Sign in when prompted. Your session is saved to ~/.familysearch-mcp/config.json.
README
以下为原文 README 节选,完整内容请查看原文。
FamilySearch MCP Server
A local Model Context Protocol (MCP) server for FamilySearch. Gives AI assistants access to search the Family Tree, view person details, explore ancestors and descendants, and search historical records.
Features
- Family Tree search — find individuals by name, dates, places, and gender
- Person details — view a person card by ID
- Pedigree exploration — ancestors (up to 8 generations) and descendants (up to 3)
- Historical records — search record collections
- Browser session auth — log in once with Brave; no FamilySearch API key required
How it works
FamilySearch does not approve direct API access for most personal projects. This server reuses your browser session cookies and calls the same internal /service/ endpoints the website uses. Your session is stored locally at ~/.familysearch-mcp/config.json.
Prerequisites
- Node.js 18+ and npm
- Brave browser — Playwright’s bundled Chromium is blocked by FamilySearch bot detection
- A free FamilySearch account
Installation
1. Clone and build
git clone https://github.com/JonathanReiss15/familysearch-mcp.git
cd familysearch-mcp
npm install
npm run build
2. Log in to FamilySearch
npm run login
This opens Brave with a dedicated profile. Sign in when prompted. Your session is saved to ~/.familysearch-mcp/config.json.
Tip: You can also ask your AI assistant to run the
login-with-browsertool after the MCP is connected.
3. Configure your MCP client
Add the server to your client using stdio transport. Replace /path/to/familysearch-mcp with the absolute path to this repo.
Recommended config (uses cwd so you don’t need absolute paths in args):
{
"mcpServers": {
"familysearch": {
"command": "node",
"args": ["build/index.js"],
"cwd": "/path/to/familysearch-mcp"
}
}
}
Run npm run build whenever you pull changes.
MCP client setup
Cursor
Project-scoped — create .cursor/mcp.json in your project (or add globally in Cursor Settings → MCP):
{
"mcpServers": {
"familysearch": {
"command": "node",
"args": ["build/index.js"],
"cwd": "/path/to/familysearch-mcp"
}
}
}
Restart Cursor or reload MCP servers after saving.
Claude Desktop
Edit claude_desktop_config.json:
| Platform | Config path |
|---|---|
| macOS | ~/Library/Application Support/Claude/claude_desktop_config.json |
| Windows | %APPDATA%\Claude\claude_desktop_config.json |
{
"mcpServers": {
"familysearch": {
"command": "node",
"args": ["build/index.js"],
"cwd": "/path/to/familysearch-mcp"
}
}
}
Restart Claude Desktop after saving.
Claude Code
From the repo directory:
claude mcp add familysearch -- node build/index.js
安装
This server does not publish a one-line install command.
Open the repository installation guide 新手?先看 mcpskill.org 教程 →配置
{
"mcpServers": {
"familysearch": {
"command": "node",
"args": ["build/index.js"],
"cwd": "/path/to/familysearch-mcp"
}
}
}