How to Use the National Archives Catalog MCP in Vercel AI SDK

Q: How do I search the National Archives Catalog using the Vercel AI SDK?

Use createMCPClient to connect, then pass the tools directly to streamText. Your agent will call searchrecords to find historical files and display them.

Q: Can I write tags back to the National Archives Catalog with Vercel AI SDK?

Yes. You can configure your agent to call createtag or updatetranscription when a user edits a record in your frontend app.

Q: Can I moderate comments on this server?

Yes, the server exposes admin tools. Your agent can call deletecomment or getjustifications to manage community-submitted text.

Feed historical records from the National Archives Catalog directly into your Next.js frontend using the Vercel AI 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 Vercel AI SDK

Create your Vinkius account to connect National Archives Catalog to Vercel AI 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream NARA Records Direct to UI

Your users don't want to stare at a loading spinner while searching through millions of government documents. By coupling this MCP Server with the Vercel AI SDK, you can pipe raw text and metadata straight to the browser. As your agent hits `search_records` or `search_records_by_text`, the results render on screen instantly. This means you can build real-time search interfaces for historical research. If a user asks for Civil War photographs, the agent grabs the data and streams the image URLs and descriptions before the full payload even finishes loading.

Direct Citizen Archiving in React

Let users transcribe old handwriting or tag photos without complex backend plumbing. This integration lets your Vercel AI SDK setup call `create_transcription` or `create_tag` directly from an Edge Function. The AI UI updates on the fly, showing the new contribution as soon as NARA logs it. You can also pull up-to-date community additions in real-time. Use `get_transcriptions_by_naid` or `get_tags_by_naid` to render user-generated metadata right alongside official archival records in your custom dashboard.

Build Live Contribution Dashboards with Vercel AI SDK

Track what your community is doing across the platform. This MCP Server lets your application fetch specific user histories instantly. By calling `get_contributions_by_userid` or `get_record_stats`, your UI can display live statistics and user notifications without lag. If a user wants to check their past work, the agent invokes `get_transcription_history` to pull their edits. The Vercel AI SDK handles this asynchronously, rendering a clean timeline of their historical archival contributions.

Setup guide

Set up National Archives Catalog MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all National Archives Catalog tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent National Archives Catalog transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Use `createMCPClient` to connect, then pass the tools directly to `streamText`. Your agent will call `search_records` to find historical files and display them.

Yes. You can configure your agent to call `create_tag` or `update_transcription` when a user edits a record in your frontend app.

The SDK streams text chunks as they arrive. If the agent needs to pull heavy metadata, it calls `fetch_coords` or `get_record_children` to chunk the UI response.

Yes, the server exposes admin tools. Your agent can call `delete_comment` or `get_justifications` to manage community-submitted text.

Your search queries for historical records and user comments flow securely. Vinkius runs this MCP Server in an isolated, zero-trust sandbox, so your session keys and transcriptions never touch external logs.

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