How to Use the National Archives Catalog MCP in Mastra AI

Q: How does Mastra AI connect to the National Archives Catalog MCP Server?

Instantiate the MCPClient with the Vinkius endpoint URL. Then, pass the catalog tools directly into your Mastra agent configuration to start querying.

Q: Can I build multi-step research agents using Mastra AI and the National Archives Catalog?

Yes. You can chain tools like searchrecordsbytext and getcommentsbynaid into a single workflow to compile detailed research briefs.

Q: How do I handle rate limits on the National Archives Catalog with Mastra AI?

Mastra AI features built-in retry logic. If a tool like gettranscriptionhistory fails due to API limits, the workflow automatically backs off and retries.

Q: Can I manage user accounts on NARA?

Yes. You can use tools like getusers and updateuser to manage local contributor profiles and roles within your custom application.

Build resilient workflows that query and edit the National Archives Catalog using Mastra AI agents.

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 Mastra AI

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fail-safe Archival Workflows

NARA's API can be slow or rate-limit you when pulling massive record sets. Mastra AI solves this by wrapping National Archives Catalog queries in workflows with automatic retries and exponential backoff. If `search_records` hits a temporary block, the workflow pauses and retries without crashing your app. You can build complex branching logic based on what the archives return. For example, if `get_record_children` returns zero results, your workflow can branch to try `search_records_by_tag` instead to find related historical files.

Approve Transcriptions via Mastra AI Workflows

Crowdsourcing history is messy, so you need a human gatekeeper before pushing edits. This MCP Server allows your Mastra AI setup to pause workflows when an agent attempts to write data. When the agent triggers `create_transcription` or `update_comment`, the workflow stops and waits for admin authorization. Once approved, the agent executes the write operation and logs the action. This keeps your community-driven archive project clean while preventing spam from hitting the official database.

Automate Contributor History Audits

Track and verify contributor behavior across thousands of records automatically. This MCP Server exposes tools like `get_contributions_by_userid` and `get_user` to audit active accounts. Mastra AI can run scheduled agents to flag suspicious activity patterns. If a user starts spamming low-quality comments, the agent can trigger `delete_contributions` or `delete_tag` to clean up the catalog. The workflow handles the cleanup sequence step-by-step and notifies your team.

Setup guide

Set up National Archives Catalog MCP in Mastra AI

Prerequisites

Node.js 18+ and a TypeScript project
@mastra/mcp + @mastra/core packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run npm install @mastra/mcp @mastra/core plus your preferred model provider (e.g. @ai-sdk/openai).
2

Configure the MCPClient
Create an MCPClient with your Vinkius endpoint as a URL object. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and inject tools
Call mcpClient.listTools() and spread the result into your agent's tools object. All National Archives Catalog tools become native Mastra tools.
4

Run with any model
Swap openai("gpt-4o") for any AI SDK-compatible provider. Call agent.generate() and the agent routes tool calls through MCP automatically.

agent.ts

import { MCPClient } from "@mastra/mcp";
import { Agent } from "@mastra/core/agent";
import { openai } from "@ai-sdk/openai";

const mcpClient = new MCPClient({
  id: "national-archives-catalog-mcp-client",
  servers: {
    "national-archives-catalog-mcp": {
      url: new URL(
        "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
      ),
    },
  },
});

const agent = new Agent({
  name: "National Archives Catalog Agent",
  model: openai("gpt-4o"),
  instructions: "You have access to National Archives Catalog tools.",
  tools: {
    ...(await mcpClient.listTools()),
  },
});

const result = await agent.generate(
  "List recent National Archives Catalog transactions"
);
console.log(result.text);

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 Mastra AI

Instantiate the `MCPClient` with the Vinkius endpoint URL. Then, pass the catalog tools directly into your Mastra agent configuration to start querying.

Yes. You can chain tools like `search_records_by_text` and `get_comments_by_naid` into a single workflow to compile detailed research briefs.

Mastra AI features built-in retry logic. If a tool like `get_transcription_history` fails due to API limits, the workflow automatically backs off and retries.

Yes. You can use tools like `get_users` and `update_user` to manage local contributor profiles and roles within your custom application.

Your search parameters, tags, and comments pass through this MCP Server's ephemeral, zero-trust sandbox. Session keys and historical queries are never stored or exposed to third parties.

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