How to Use the National Archives Catalog MCP in LlamaIndex

Q: How do I use LlamaIndex to create a searchable index of Civil War records from the National Archives Catalog?

First, use the searchrecordsbytext tool to find all records matching 'Civil War'. Then, loop through the results, using getrecordchildren or gettranscriptionsbynaid to get more data. As you retrieve the data, you load it into a LlamaIndex VectorStoreIndex for querying.

Q: Can I use LlamaIndex to ask questions about user contributions in the National Archives Catalog?

Yes. You can build a data loader that uses getcontributionsbyuserid or searchcomments to pull contribution data into an index. Once indexed, you can ask your RAG application natural language questions about that user's activity or specific comments.

Build a knowledge base from National Archives records. Ground your LlamaIndex RAG apps in verifiable historical data.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect National Archives Catalog MCP to LlamaIndex

Create your Vinkius account to connect National Archives Catalog 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 National Archives Catalog with LlamaIndex

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Index Live Archive Data

This MCP Server connects your LlamaIndex application directly to the National Archives. Use the `McpToolSpec` to turn all 40 NARA tools into functions your agent can call. You can run a query with `search_records` and automatically feed the results into a vector index. This isn't just about calling an API. It's about building a durable, searchable knowledge base from the results. Once indexed, your agent can perform semantic searches over the records it's already found, reducing redundant API calls and grounding its responses in data you've already retrieved and processed.

Augment Records with Contribution Data

Your agent can enrich its knowledge base by pulling in community-generated content. After finding a record with `search_records_by_tag`, your agent can then call `get_comments_by_naid` and `get_transcriptions_by_naid` to fetch all related user contributions. By indexing this metadata alongside the original record, you create a much richer data source. Your RAG application can then answer questions not just about the record itself, but about how it has been interpreted and discussed by the community. This provides a layer of context that a simple document search can't.

Build a Smarter RAG Query Engine

LlamaIndex turns the 40 tools of this MCP Server into a dynamic data source for your query engine. You can build an agent that decides whether to query its existing index or fetch fresh data from the NARA API. For example, if a question is about recent contributions, it can use `search_contributions` to get the latest data. This hybrid approach—combining a static index with live tool-based lookups—gives you the best of both worlds. You get the speed of a local vector search and the real-time accuracy of a direct API call, all managed by your LlamaIndex agent.

Setup guide

Set up National Archives Catalog 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 National Archives Catalog 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 National Archives Catalog tools.",
)
response = await agent.run("List recent National Archives Catalog 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 National Archives Catalog. 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 National Archives Catalog 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 National Archives Catalog MCP in LlamaIndex

First, use the `search_records_by_text` tool to find all records matching 'Civil War'. Then, loop through the results, using `get_record_children` or `get_transcriptions_by_naid` to get more data. As you retrieve the data, you load it into a LlamaIndex `VectorStoreIndex` for querying.

Yes. You can build a data loader that uses `get_contributions_by_userid` or `search_comments` to pull contribution data into an index. Once indexed, you can ask your RAG application natural language questions about that user's activity or specific comments.

This MCP Server provides structured access. Instead of parsing messy HTML, you get clean JSON responses from 40 distinct tools, like `get_tags_by_naid`. It's faster, more reliable, and gives you direct access to functions like adding comments or transcriptions, which you can't do with a scraper.

The underlying NARA API has rate limits. When doing a large-scale import, it's best to add a small delay between your calls to tools like `search_records` or `get_transcriptions_by_naid` to avoid getting throttled. The MCP connection itself doesn't add extra limits.

The MCP Server processes your requests for NARA data, like record IDs or user contribution text. That data is then returned to your LlamaIndex application, where you control how it's indexed and stored. The security of your local vector index is your responsibility; Vinkius just ensures the secure transport of the data during the API call.

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