How to Use the National Archives Catalog MCP in OpenAI Agents SDK

Q: How do I connect the National Archives Catalog to the OpenAI Agents SDK?

Install openai-agents via pip. Create an MCPServerStreamableHttp instance with your Vinkius endpoint URL and pass it to the mcpservers array in your Agent constructor to enable the MCP tools.

Q: Can the OpenAI Agents SDK search the National Archives Catalog by specific tags?

Yes. The agent will auto-discover the searchrecordsbytag tool. You can instruct the agent to look up exact historical tags and return the matching record IDs.

Q: Does the National Archives Catalog MCP Server support reading historical transcriptions?

It does. Your agent can call gettranscription for a specific ID or use gettranscriptionsbynaid to pull all transcribed text attached to a single archival record.

Q: How do I moderate user comments in the National Archives Catalog using the OpenAI Agents SDK?

You can build an admin agent with access to the deletecomment and deletecontributions tools. Set up OpenAI guardrails to require human approval before the agent executes these destructive actions.

Build production-grade research agents that query the National Archives Catalog using the OpenAI Agents SDK.

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 OpenAI Agents SDK

Create your Vinkius account to connect National Archives Catalog to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Query millions of NARA records via MCP Server

The `search_records` and `search_records_by_text` tools give your OpenAI agents direct access to the US National Archives. You can build specialized research agents that dig through historical documents, photos, and metadata without hallucinating facts. Handoffs make this powerful. You might have one agent find primary sources using `search_records_by_tag`, then hand the record ID to a transcription agent that calls `get_transcriptions_by_naid` to pull the exact text. Every call gets logged in your OpenAI dashboard for full tracing.

Manage crowdsourced historical data

NARA isn't just a static database. It relies on user contributions. Your agent can pull user-generated context using `search_comments` or `get_tags_by_naid` to see how historians categorize specific records. If you build an internal tool for archivists, the OpenAI Agents SDK guardrails ensure safe data entry. You can configure strict validation before the agent executes `create_tag` or `create_transcription`, preventing bad data from hitting the public catalog.

Track user contributions and history

Community engagement leaves a massive footprint. Tools like `get_contributions_by_userid` and `get_transcription_history` let your agent audit exactly who modified what. This is crucial for production systems that need to verify the credibility of a transcription. Instead of trusting a raw text dump, your agent can pull the full edit history and user stats via `get_record_stats` before including the data in a final report.

Setup guide

Set up National Archives Catalog MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all National Archives Catalog tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives National Archives Catalog tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate National Archives Catalog tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="National Archives Catalog Agent",
            instructions="You have access to National Archives Catalog tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

Install `openai-agents` via pip. Create an `MCPServerStreamableHttp` instance with your Vinkius endpoint URL and pass it to the `mcp_servers` array in your Agent constructor to enable the MCP tools.

Yes. The agent will auto-discover the `search_records_by_tag` tool. You can instruct the agent to look up exact historical tags and return the matching record IDs.

It does. Your agent can call `get_transcription` for a specific ID or use `get_transcriptions_by_naid` to pull all transcribed text attached to a single archival record.

You can build an admin agent with access to the `delete_comment` and `delete_contributions` tools. Set up OpenAI guardrails to require human approval before the agent executes these destructive actions.

Vinkius isolates your connection in an ephemeral V8 sandbox. When your agent fetches historical metadata or user IDs via `get_user` using the MCP protocol, the request routes directly to NARA. We hold no logs of your specific search queries.

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