How to Use the Internet Archive Search MCP in Vercel AI SDK

Q: How do I stream Internet Archive Search results using the Vercel AI SDK?

You call createMCPClient to connect to the hosted MCP Server endpoint and pass its tools to streamText. The SDK then streams the metadata from tools like search directly to your frontend components. This lets you display historical records to users as the model finds them.

Q: How does the Vercel AI SDK handle pagination for Internet Archive Search?

You pass the page parameter from your UI to the search tool inside the SDK's tool call loop. This allows your users to trigger subsequent pages of historical data without losing the active chat context. The SDK manages the state and appends the new results to your UI feed.

Q: Can I filter by file format when querying the archive with this SDK?

Yes, you can use the searchbymediatype tool within your tool-calling configuration. The model will automatically recognize if the user wants audio, books, or software, and apply the correct filter. Your React components then receive only the matching file formats.

Stream Internet Archive Search results directly into your React components in real time 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 Internet Archive Search MCP to Vercel AI SDK

Create your Vinkius account to connect Internet Archive Search 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 Internet Archive Search with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream Archive Metadata with Vercel AI SDK

Your React frontend no longer has to wait for massive historical datasets to load before showing anything to the user. When your agent triggers `search` or `faceted_search` on this MCP Server, the Vercel AI SDK streams the raw metadata chunks straight to the UI. Your users see books, videos, and old software titles populate their screens in real-time, completely skipping the annoying blank loading screens. This setup runs entirely on the edge, keeping your API calls cheap and fast. You get to map the structured JSON output of `faceted_search` directly to custom UI charts, showing media distributions or creator breakdowns as the AI agent parses the query.

Narrow Down 40M+ Records on the Edge

Stop fetching massive payloads only to filter them on the client side. By combining the Vercel AI SDK with `search_by_date_range` and `search_by_language`, your app requests only the precise slice of history it needs. If a user asks for 1950s Spanish radio plays, the SDK feeds those specific parameters to the MCP Server, keeping the edge function execution time minimal. You can also configure your interface to let users instantly pivot their search. When they click a creator name, the SDK triggers `search_by_creator` to fetch and render the author's entire catalog without forcing a full page reload.

Feed Popular Media Directly to Your UI

Let your users discover historical gems without manual browsing. This MCP Server lets you pull the most active files using `search_top_downloads` and render them in a streaming list via the Vercel AI SDK. Whether they want classic movies or vintage software, the live download counts populate your components instantly. For deeper research, the agent can call `search_fulltext` to scan descriptions of old manuscripts. The Vercel AI SDK handles the text chunking, so your users can watch the relevant historical context fill their screens sentence by sentence.

Setup guide

Set up Internet Archive Search 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 Internet Archive Search 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 Internet Archive Search 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 Internet Archive Search. 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 Internet Archive Search 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 Internet Archive Search MCP in Vercel AI SDK

You call `createMCPClient` to connect to the hosted MCP Server endpoint and pass its tools to `streamText`. The SDK then streams the metadata from tools like `search` directly to your frontend components. This lets you display historical records to users as the model finds them.

Yes, this setup is fully compatible with edge runtimes. The SDK connects to the MCP Server via a lightweight HTTP transport, avoiding heavy Node.js dependencies. This keeps your edge function startup times low while querying millions of archive items.

You pass the page parameter from your UI to the `search` tool inside the SDK's tool call loop. This allows your users to trigger subsequent pages of historical data without losing the active chat context. The SDK manages the state and appends the new results to your UI feed.

Yes, you can use the `search_by_mediatype` tool within your tool-calling configuration. The model will automatically recognize if the user wants audio, books, or software, and apply the correct filter. Your React components then receive only the matching file formats.

Your search queries and archive identifiers are processed in an isolated V8 sandbox that wipes all memory after execution. No search history is stored on Vinkius servers, keeping your research completely private. The connection between your SDK client and the server uses secure, encrypted transport protocols.

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