How to Use the National Archives Catalog MCP in LangChain

Q: How can I use LangChain to find specific photos in the National Archives Catalog?

You'd equip your agent with the searchrecords tool. In your chain, you can construct a query that specifies image as the media type and adds keywords. The agent gets back a list of records with IDs, which you can then pass to other tools like gettagsbynaid for more context.

Q: Can my LangChain agent transcribe a document from the National Archives Catalog?

Yes. The agent would first use a search tool like searchrecordsbytext to find the document's ID. Then, it calls createtranscription with that ID and the text. This adds your transcription directly to the catalog's public record.

Q: What's the best way to handle multiple tools with a LangChain agent for the National Archives Catalog?

Use createagent and pass it the full list of tools from the MCP client. This lets the agent's reasoning engine decide which tool to use—searchrecordsbytag, getcommentsbyuserid, or another—based on the user's request. It's more flexible than hardcoding a specific chain.

Build agents that query, transcribe, and tag historical records. Connect your LangChain apps to the National Archives.

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 LangChain

Create your Vinkius account to connect National Archives Catalog to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain Historical Research Tasks

This MCP Server gives your LangChain agent 40 tools to interact with the US National Archives. You can build chains that replicate a real research workflow. For example, an agent can start with a broad `search_records_by_text` query, find a promising document, and then pass its ID to `get_transcriptions_by_naid` to check for existing user work. If no transcription exists, the next step in your chain can call `create_transcription` to add one. Or, it can use `get_record_children` to explore related materials in the same collection. Every call is just another link in the chain, letting your agent reason its way through the archives instead of just fetching data.

Manage Crowdsourced Contributions

Go beyond just reading data. Your agent can actively contribute to the catalog. Use `create_tag` and `create_comment` to add context to records, or `update_transcription` to improve existing text. It's a two-way street—your agent can also check the work of others. Build a quality-control agent that uses `get_transcription_history` to review changes or `get_comments_by_naid` to assess public feedback on a record. This MCP Server lets you build agents that don't just consume historical data, but actively help curate it.

Build Custom Research Pipelines

The toolset is designed for creating complex, stateful research agents. Your agent can pull a list of its own past work with `get_contributions_by_userid` to avoid duplicating effort. It can also manage its own identity in the catalog by using `get_user` and `update_user`. By combining these tools in a LangChain graph, you build agents that do more than just answer one-off questions. They can perform long-running tasks, maintain a profile, and interact with the NARA community's contributions over time. This is how you automate deep archival work.

Setup guide

Set up National Archives Catalog MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes National Archives Catalog tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "national-archives-catalog-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent National Archives Catalog transactions"
    })
    print(result["messages"][-1].content)

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 LangChain

You'd equip your agent with the `search_records` tool. In your chain, you can construct a query that specifies `image` as the media type and adds keywords. The agent gets back a list of records with IDs, which you can then pass to other tools like `get_tags_by_naid` for more context.

Yes. The agent would first use a search tool like `search_records_by_text` to find the document's ID. Then, it calls `create_transcription` with that ID and the text. This adds your transcription directly to the catalog's public record.

Use `create_agent` and pass it the full list of tools from the MCP client. This lets the agent's reasoning engine decide which tool to use—`search_records_by_tag`, `get_comments_by_userid`, or another—based on the user's request. It's more flexible than hardcoding a specific chain.

No, Vinkius handles it. You get a single endpoint token for this MCP Server. Your LangChain agent just makes the tool calls; the underlying MCP client manages the connection and authentication securely.

Your queries and any data you contribute, like comments or tags, pass through the Vinkius MCP Server to the National Archives. Vinkius operates on a zero-trust, ephemeral basis. It processes the tool call and forwards it, but doesn't store your specific search terms or contribution content after the job is done.

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