How to Use the National Archives Catalog MCP in AutoGen

Q: How can I set up two AutoGen agents to collaborate on research in the National Archives Catalog?

First, load the tools using mcpservertools. Assign the full toolset to an AssistantAgent that acts as a proxy. Then create two other agents without tools—a 'Researcher' and a 'Fact-Checker'—and have them discuss the task. The proxy agent will execute tool calls like searchrecords on their behalf.

Q: Is this difficult to set up in AutoGen?

No, it's straightforward. The autogen-extmcp package gives you a mcpservertools function. You just provide your Vinkius endpoint URL, and it returns a list of tools ready to be passed to your AssistantAgent constructor. The adapter handles all the schema conversions.

Deploy teams of agents that debate, research, and curate records from the US National Archives using AutoGen.

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 AutoGen

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enable Multi-Agent Research Debates

This MCP Server gives your AutoGen agents the tools to conduct sophisticated research. You can create a 'Researcher' agent that uses `search_records_by_text` to find primary sources. Then, a 'Critic' agent can challenge its findings, using `get_comments_by_naid` to check for conflicting public opinions on the same record. This isn't a simple query-response loop. It's a conversation. The agents can debate the reliability of a source, with one agent using `get_transcription_history` to spot heavy revisions while another uses `get_record_stats` to gauge its popularity. They work together to reach a more robust conclusion.

Automate Content Curation Teams

Deploy a team of agents to improve the catalog. One agent's job is to find untranscribed documents. It uses `search_records` to find files and `get_transcriptions_by_naid` to check their status. When it finds one, it passes the task to a 'Scribe' agent that uses an external model to generate text and submits it with `create_transcription`. A third 'Auditor' agent can then periodically review contributions using `get_contributions_by_userid`. This creates a fully autonomous pipeline where agents collaborate to identify, execute, and verify curation tasks within the National Archives.

Simulate Historical Analysis with this MCP Server

The 40 tools in this MCP Server are perfect for building complex, conversational systems in AutoGen. You can set up agents with different roles and perspectives. An 'Archivist' agent could focus on metadata and provenance, using `get_record_children`, while a 'Genealogist' agent prioritizes finding personal connections with `search_records_by_tag`. When given a research goal, these agents converse, each using the tools best suited for their role. The final output is a result of their negotiated process, not a single agent's effort. It's a way to model collaborative problem-solving for historical research.

Setup guide

Set up National Archives Catalog MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes National Archives Catalog tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="National Archives Catalog_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent National Archives Catalog data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="National Archives Catalog_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent National Archives Catalog data")
    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 AutoGen

First, load the tools using `mcp_server_tools`. Assign the full toolset to an `AssistantAgent` that acts as a proxy. Then create two other agents without tools—a 'Researcher' and a 'Fact-Checker'—and have them discuss the task. The proxy agent will execute tool calls like `search_records` on their behalf.

Yes. If an agent has access to the toolset, it can decide to call `create_tag`. In a multi-agent setup, one agent might propose a tag, and another might have to approve it before the final `create_tag` call is executed. It's all part of the conversation.

Consensus. For complex tasks like assessing a historical source's bias, a single agent might miss things. AutoGen lets you create a 'skeptic' agent that actively questions the findings of a 'researcher' agent, using tools like `get_comments_by_naid` to find counter-arguments. This leads to more reliable results.

No, it's straightforward. The `autogen-ext[mcp]` package gives you a `mcp_server_tools` function. You just provide your Vinkius endpoint URL, and it returns a list of tools ready to be passed to your `AssistantAgent` constructor. The adapter handles all the schema conversions.

The content of your agent conversations stays in your environment. When an agent decides to use a tool, only the specific tool call—like a search query or the text for a new `create_comment`—is sent through the Vinkius MCP Server. The server itself is stateless and doesn't retain a history of your agents' debates.

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