How to Use the Guru MCP in Vercel AI SDK

Q: How do I connect Guru to my Vercel AI SDK project?

Install the @ai-sdk/mcp package and initialize the client with your Vinkius endpoint. Pass the tools from mcpClient.tools() into your streamText function. Don't forget to call mcpClient.close() when the session ends.

Q: Can I search my Guru wiki in real-time with Vercel AI SDK?

Yes. The searchknowledgebase tool runs through the SDK to stream search results directly into your frontend. Users see the raw wiki data populate their screens instantly.

Q: How does Vercel AI SDK handle Guru collection metadata?

It uses the getcollectiondetails tool to pull metadata directly into your application context. This lets your agent make decisions based on collection-specific rules before displaying content.

Stream real-time wiki searches and card updates directly into your React UI 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 Guru MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Real-time wiki search in your React UI

This Guru MCP Server exposes the `search_knowledge_base` tool to let your application fetch and render wiki content on the fly. Your UI streams the results instantly as the model finds them. You don't have to write complex API wrappers. Just pull the cards using `get_card_details` and feed them straight to your frontend components.

Live documentation updates with Vercel AI SDK

Use `create_knowledge_card` to let users edit and create wiki entries without leaving your application. Your AI client can trigger updates based on user input, updating Guru in the background. The SDK pipes the operation status back to the client immediately. If a team member needs to fix a typo, the model runs `update_knowledge_card` and displays the updated text in the interface.

Instant taxonomy mapping

The `list_knowledge_collections` tool helps your agent keep track of where information belongs inside the MCP Server. Keeping track of taxonomy manually is a massive pain. Your agent reads the current structure, maps the incoming data, and places it in the right spot. This keeps your knowledge base organized without manual sorting.

Setup guide

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

Install the `@ai-sdk/mcp` package and initialize the client with your Vinkius endpoint. Pass the tools from `mcpClient.tools()` into your `streamText` function. Don't forget to call `mcpClient.close()` when the session ends.

Yes. The `search_knowledge_base` tool runs through the SDK to stream search results directly into your frontend. Users see the raw wiki data populate their screens instantly.

It uses the `get_collection_details` tool to pull metadata directly into your application context. This lets your agent make decisions based on collection-specific rules before displaying content.

No. Vinkius handles the authentication securely on the backend. Your code only needs a single MCP endpoint token to execute tools like `list_knowledge_cards` safely.

Your wiki cards, collection details, and search queries never touch public LLMs directly. Vinkius runs this connector in an isolated, ephemeral sandbox, passing data only to your specified endpoint.

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