Skip to main content
Glama
wikitree-mcp

wikitree-mcp

wikitree-mcp

MCP server exposing WikiTree's genealogy API via the Code Mode architecture. Public profiles only — no authentication required.

Note: GitHub is a read-only mirror. Development happens on GitLab.

Architecture

This server uses 2 meta-tools (search + execute) with 10 operations in a server-side registry. The LLM discovers operations via search and runs them via execute.

Tool

Description

search

Discover available operations and their parameters

execute

Run a named operation against the WikiTree API

Operations

Operation

Category

Description

get_profile

read

Retrieve a person or free-space profile

get_person

read

Retrieve a person profile (person profiles only)

get_people

read

Fetch multiple profiles by keys or relationships

search_person

search

Search profiles by name, dates, location, gender

get_ancestors

analysis

Get ancestor tree (parents, grandparents, etc.)

get_descendants

analysis

Get descendant tree (children, grandchildren, etc.)

get_relatives

read

Get parents, children, siblings, spouses

get_bio

content

Retrieve biography text

get_photos

content

Get photos linked to a profile

get_categories

content

Retrieve associated categories

Related MCP server: Gramps MCP

Configuration

Environment Variable

Required

Default

Description

WIKITREE_APP_ID

No

Genealogy-MCP_wikitree-mcp

Your application identifier for the WikiTree API

WIKITREE_API_BASE_URL

No

https://api.wikitree.com/api.php

WikiTree API endpoint

WIKITREE_HTTP_TIMEOUT

No

10.0

HTTP request timeout in seconds

WIKITREE_MAX_RETRIES

No

3

Max retry attempts for transient failures

Setup: Claude Desktop

Add to your claude_desktop_config.json:

Using uv (local)

{
  "mcpServers": {
    "wikitree": {
      "command": "uv",
      "args": ["--directory", "/path/to/wikitree-mcp", "run", "wikitree-mcp"],
      "env": {
        "WIKITREE_APP_ID": "your-app-id"
      }
    }
  }
}

Using Docker

{
  "mcpServers": {
    "wikitree": {
      "command": "docker",
      "args": ["run", "-i", "--rm", "-e", "WIKITREE_APP_ID=your-app-id", "wikitree-mcp"]
    }
  }
}

Setup: Claude Code

Using uv (local)

claude mcp add wikitree -- uv --directory /path/to/wikitree-mcp run wikitree-mcp

Set the environment variable:

export WIKITREE_APP_ID=your-app-id

Using Docker

claude mcp add wikitree -- docker run -i --rm -e WIKITREE_APP_ID=your-app-id wikitree-mcp

Development

make install       # Install dependencies
make test          # Run tests with coverage (mocked, no network)
make test-live     # Run live tests against real WikiTree API
make ci            # Full CI pipeline (lint + typecheck + test + audit)
make format        # Auto-format code
make build         # Build wheel
make run           # Run with streamable-http on port 8000
make run-stdio     # Run with stdio transport

License

AGPL-3.0-only

Available Tools

2 tools
executeA
Read-only

Run a named operation against the WikiTree API. Use 'search' first to discover the exact operation name and its params schema, then call this with {operation: '...', params: {...}}.

Inputs: arguments (required). Returns: result

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4.3/5.0

    Scored across 2 tools

    Disambiguation5/5

    The tools 'search' and 'execute' have clearly distinct purposes: one discovers operations and schemas, the other executes them. No overlap.

    Naming Consistency5/5

    Both tools use simple, consistent verb-only names ('search', 'execute') that clearly reflect their actions.

    Tool Count3/5

    With only 2 tools, the surface seems thin, but the design intentionally uses a meta-pattern where 'search' discovers API operations. This can be appropriate for a large dynamic API, though it may feel sparse.

    Completeness3/5

    The discover-execute pattern covers the basic interaction with the WikiTree API, but it lacks direct CRUD tools and relies entirely on dynamic discovery, which may leave gaps in common workflows.

    Maintenance

    ActivityNo data
    ResponsivenessOutdated data

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      Not graded
      quality
      B
      maintenance
      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.
      17
      MIT
    • A
      license
      Not graded
      quality
      D
      maintenance
      Enables AI assistants to interact with Gramps genealogy databases for intelligent family tree research and management. Provides comprehensive tools for searching family data, creating records, analyzing relationships, and tracking genealogy research through natural language.
      52
      AGPL 3.0
    • A
      license
      B
      quality
      D
      maintenance
      Integrates with the WikiTree API to provide tools for exploring genealogical data, including ancestor and descendant information. It enables users to retrieve biographies and family relationships through any application supporting the Model Context Protocol.
      5
      1
      Apache 2.0