How to Use the Typesense Vector Search MCP in Vercel AI SDK

Q: How do I use Typesense Vector Search with Vercel AI SDK?

You call searchvectors, passing your collection name, text query, and vector string. The client processes this immediately and streams the findings to your React or Next.js frontend.

Q: Can I manage collections using Typesense Vector Search with Vercel AI SDK?

Yep. You can use createcollection to build out a new schema, or getcollectiondetails if you just need to check the current structure and metadata.

Q: Is the full range of tools available for Vercel AI SDK?

Yes. The MCP Server provides six core functions: createcollection, deletedocument, getcollectiondetails, indexdocument, listvectorcollections, and searchvectors.

Stream live vector search results into your UI with 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 Typesense Vector Search MCP to Vercel AI SDK

Create your Vinkius account to connect Typesense Vector 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 Typesense Vector Search with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run Vector Search from the Vercel AI SDK

You use `search_vectors` to perform a deep semantic lookup. Give it a collection name, a text query, and your vector string (e.g., "vec:(0.1, 0.2, ...)"). Your agent client executes this call and gets back the top matching documents. The AI SDK handles streaming these results directly to the user interface. Users see data populate in real-time—no loading spinner required.

Manage Search Data via MCP Server

Need to set up a new knowledge base? Call `create_collection` and pass it your specific JSON schema details. This defines the structure for all future searches in that collection. Want to update or add data? Use `index_document`. Just give the collection name and the document payload, and it's stored and ready for vector lookup.

Maintain Search Integrity with Vercel AI SDK

When a collection is obsolete, you can wipe it out using `delete_document`. Be careful; this action permanently removes the data and cannot be undone. If you're unsure what exists or what structure is active, run `list_vector_collections` to see every available search resource within the Typesense MCP Server.

Setup guide

Set up Typesense Vector 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 Typesense Vector 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 Typesense Vector 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 Typesense Vector 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 Typesense Vector 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 Typesense Vector Search MCP in Vercel AI SDK

You call `search_vectors`, passing your collection name, text query, and vector string. The client processes this immediately and streams the findings to your React or Next.js frontend.

Yep. You can use `create_collection` to build out a new schema, or `get_collection_details` if you just need to check the current structure and metadata.

The tool will accept the document payload, so ensure your input JSON is valid before calling `index_document`. If the structure is wrong, you'll get an error back through the stream.

This server touches search collection schemas and document content. Because it uses Typesense Vector Search, all data remains within your defined collections.

Yes. The MCP Server provides six core functions: `create_collection`, `delete_document`, `get_collection_details`, `index_document`, `list_vector_collections`, and `search_vectors`.

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