How to Use the National Archives Catalog MCP in Pydantic AI

Q: How do I add the National Archives Catalog to a Pydantic AI agent?

Install pydantic-ai-slimmcp. Initialize an MCPToolset with your HTTP endpoint URL and pass it to the toolsets array when defining your Agent.

Q: Can Pydantic AI agents read user comments from the National Archives Catalog?

Yes. The agent can execute getcommentsbynaid to pull all discussion threads attached to a specific historical record.

Q: Does the National Archives Catalog MCP Server support creating new transcriptions?

It does. Your agent can use the createtranscription or updatetranscription tools to submit text. Pydantic will validate the schema before the API call fires.

Build type-safe historical research tools that query the National Archives Catalog via Pydantic AI.

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 Pydantic AI

Create your Vinkius account to connect National Archives Catalog to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe NARA record retrieval

Historical APIs are notorious for inconsistent metadata. When your Pydantic AI agent calls `search_records` or `get_record_children`, the responses are strictly validated against your Pydantic models. If NARA returns an unexpected field format for a document date, the agent fails loudly. You catch the validation error immediately instead of letting silent corruption ruin your research dataset.

Validate archival transcriptions and tags

Pulling crowdsourced data requires strict type checking. Your agent can fetch user-generated content using `get_transcriptions_by_naid` or `get_tags_by_naid` and map the output directly to typed Python objects. This guarantees that every transcription you process has the exact structure you expect. If you use the `create_tag` tool to write back to the catalog, Pydantic ensures your payload perfectly matches the required NARA schema before the request even leaves your server.

Audit user contributions via MCP Server

Tracking who modifies historical records demands precision. Tools like `get_contributions_by_target_naid` and `get_transcription_history` allow your agent to pull detailed audit logs for any document. You can define strict models for user statistics and pipe the output of `get_record_stats` right into them. Because Pydantic AI is model-agnostic, you can use a cheap local model to parse the history and a larger Anthropic model to summarize the findings.

Setup guide

Set up National Archives Catalog MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "national-archives-catalog-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to National Archives Catalog tools.",
)

result = await agent.run("List recent National Archives Catalog transactions")
print(result.output)

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 Pydantic AI

Install `pydantic-ai-slim[mcp]`. Initialize an `MCPToolset` with your HTTP endpoint URL and pass it to the `toolsets` array when defining your Agent.

Yes. The agent can execute `get_comments_by_naid` to pull all discussion threads attached to a specific historical record.

It does. Your agent can use the `create_transcription` or `update_transcription` tools to submit text. Pydantic will validate the schema before the API call fires.

Define your Pydantic models with optional fields for historical records. When `search_records_by_text` returns sparse data, the validation will pass while keeping the exact schema intact.

Vinkius handles auth securely in an isolated V8 environment. When your agent requests contributor profiles or justification logs via `get_justifications` over the MCP protocol, the transaction is ephemeral. We never cache your typed historical data.

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