How to Use the AddSearch MCP in Vercel AI SDK

Q: How does AddSearch handle streaming responses inside Vercel AI SDK?

You call mcpClient.tools() to grab the search tools and pass them directly to streamText. The model executes searchkeyword or searchfiltered and streams the JSON payloads to your UI. This keeps your interface fast because you do not wait for the entire generation to finish before showing results.

Q: How do I handle pagination when searching indexed documents?

You use the searchpagination tool to fetch specific chunks of results. Your agent reads the current page state and requests the next batch when the user scrolls or clicks next. This prevents the context window from getting clogged with too many documents at once.

Feed live site search results and click analytics directly into your Vercel AI SDK stream without loading spinners.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect AddSearch MCP to Vercel AI SDK

Create your Vinkius account to connect AddSearch 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 AddSearch with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Render Instant Search Results in Vercel AI SDK

The `search_keyword` tool lets your agent query your indexed site content instantly. Your Vercel AI SDK client streams these raw search results straight to the user's screen in real-time, bypassing the usual API-to-UI lag. By combining this with `autosuggest`, you let the agent predict what the user wants before they even finish typing. The frontend updates dynamically as the model evaluates the search intent.

Live Document Indexing via MCP Server

The `index_document` tool gives your agent the power to modify your search index on the fly. When a user updates a post, the Vercel AI SDK triggers this tool to keep your site search fresh. You can also call `delete_document` to strip out outdated pages instantly. This ensures your site search never serves dead links to active visitors.

Stream Analytics Directly to Your Dashboard

The `stats_queries` tool pulls raw search query analytics directly into your streaming UI. Your agent reads what users are looking for and displays the top trends without making you open a separate dashboard. Pair this with `stats_clicks` to track exactly which links get the most traction. It gives you immediate visibility into user behavior right inside your custom admin panel.

Setup guide

Set up AddSearch 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 AddSearch 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 AddSearch 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 AddSearch. 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 AddSearch 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 AddSearch MCP in Vercel AI SDK

You call `mcpClient.tools()` to grab the search tools and pass them directly to `streamText`. The model executes `search_keyword` or `search_filtered` and streams the JSON payloads to your UI. This keeps your interface fast because you do not wait for the entire generation to finish before showing results.

Yes, this MCP Server is fully compatible with Edge runtimes. You initialize the connection using the Vinkius HTTP endpoint inside your route handler. It runs with minimal latency, keeping your serverless execution costs low.

Vinkius manages your secret keys securely in its hosted sandbox. Your Vercel AI SDK frontend code only talks to the secure Vinkius endpoint. This setup prevents your private API keys for `index_document` or `stats_queries` from leaking to the client browser.

You use the `search_pagination` tool to fetch specific chunks of results. Your agent reads the current page state and requests the next batch when the user scrolls or clicks next. This prevents the context window from getting clogged with too many documents at once.

Your indexed site documents, search queries, and click analytics flow directly between Vinkius and the AddSearch API over encrypted channels. Vinkius runs a zero-trust, ephemeral sandbox that never caches your raw search metrics or index content. Once the request completes, the connection tears down, keeping your proprietary search data isolated.

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