How to Use the FamilySearch API MCP in LlamaIndex

Q: Can I use the FamilySearch API to ground LlamaIndex agent responses?

Yes. By calling getpersonpedigree through the agent, the system retrieves direct ancestral records. This live data is injected into the prompt context, preventing the LLM from making up fake family histories.

Q: How do I manage large document payloads from the FamilySearch API in LlamaIndex?

Use listhistoricalcollections to filter down the target datasets before running queries. Then, chunk the text returned by getpersonmemories using LlamaIndex node parsers to keep your vector embeddings precise.

Index live genealogical records from this MCP server directly into your LlamaIndex vector stores.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect FamilySearch API MCP to LlamaIndex

Create your Vinkius account to connect FamilySearch API to LlamaIndex and route execution through our secure gateway. The platform manages server hosting, runtime updates, and security layers. Configuration requires no manual server provisioning.

GDPR Free for Subscribers

Setup FamilySearch API with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build a searchable LlamaIndex ancestral knowledge base

The `get_person_details` tool extracts full biographical profiles from the family tree to feed your LlamaIndex ingestion pipelines. Your agent pulls raw structured data and converts it into searchable document nodes. This setup lets you run semantic queries over historical records instead of relying on exact keyword matches. Outputs from `search_persons` become part of your local vector database for instant retrieval.

Ground your RAG applications in real pedigree data

This MCP server uses `get_person_pedigree` to supply your LlamaIndex RAG workflows with verified ancestral lineages. Your agent queries the live API to ground its answers, reducing hallucination rates to zero. Let's face it, remote servers go down. Before querying, the agent uses `check_api_status` to verify that the external data source is responsive. Doing this ensures your index updates do not fail silently.

Index historical documents and memories

The `get_person_memories` tool retrieves stories, photos, and written records linked to specific family members. LlamaIndex parses this unstructured text, adding rich historical context to your vector index. You can also use `list_historical_collections` to find which archives are available for indexing. This helps you narrow down search spaces before running expensive embedding operations on large datasets.

Setup guide

Set up FamilySearch API MCP in LlamaIndex

Prerequisites

Python 3.10+ installed
llama-index-tools-mcp package
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install llama-index-tools-mcp llama-index-llms-openai. The MCP tools package provides BasicMCPClient and McpToolSpec.
2

Connect with BasicMCPClient
Point BasicMCPClient to your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports SSE and Streamable HTTP transports.
3

Convert to LlamaIndex tools
Call mcp_tool_spec.to_tool_list_async() to convert all FamilySearch API MCP tools into native FunctionTool objects that any LlamaIndex agent can use.
4

Run with any LLM
Create a FunctionAgent with the tools and your preferred LLM. Swap OpenAI for Anthropic, Gemini, or any LlamaIndex-supported provider.

agent.py

from llama_index.tools.mcp import BasicMCPClient, McpToolSpec
from llama_index.core.agent.workflow import FunctionAgent
from llama_index.llms.openai import OpenAI

# Connect to the MCP
mcp_client = BasicMCPClient(
    "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)
mcp_tool_spec = McpToolSpec(client=mcp_client)

# Convert MCP tools to LlamaIndex tools
tools = await mcp_tool_spec.to_tool_list_async()

# Create and run the agent
agent = FunctionAgent(
    tools=tools,
    llm=OpenAI(model="gpt-4o"),
    system_prompt="You have access to FamilySearch API tools.",
)
response = await agent.run("List recent FamilySearch API data")

Get your connection token →

Independent Platform Disclaimer: Vinkius is an independent platform and is not affiliated with, endorsed by, sponsored by, verified by, or otherwise authorized by FamilySearch API. All third-party trademarks, logos, and brand names are the property of their respective owners. Their use on this website is strictly for informational purposes to identify service compatibility and interoperability.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

Connect FamilySearch API now

Real-time monitoring

Live

visibility into every interaction

Connect your favorite tools to your AI and see exactly what's happening — every request, every response, in real time.

Built-in savings

60%

lower AI costs

Vinkius compresses data between your apps and your AI automatically. Lower bills every month — no configuration required.

Single dashboard

One

place for every integration

Every tool your AI connects to, managed from a single screen. One account, complete control.

Common questions about FamilySearch API MCP in LlamaIndex

You load the tools via the LlamaIndex MCP tool spec and pass them to your FunctionAgent. The agent executes `search_persons` or `get_person_details` and indexes the returned payloads into your vector store.

Yes. By calling `get_person_pedigree` through the agent, the system retrieves direct ancestral records. This live data is injected into the prompt context, preventing the LLM from making up fake family histories.

Use `list_historical_collections` to filter down the target datasets before running queries. Then, chunk the text returned by `get_person_memories` using LlamaIndex node parsers to keep your vector embeddings precise.

Yes, you can pass an allowed tools list to the LlamaIndex MCP client. This restricts the agent to specific actions, like only allowing `get_person_details` while blocking broader search tools.

All genealogical records and API tokens remain inside your local environment or secure V8 sandbox. This MCP server handles authentication directly, so your private ancestral data is never exposed to external telemetry.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python

Google ADK sdk-python

Pydantic AI sdk-python

Vercel AI SDK sdk-typescript