How to Use the Cognee MCP in Vercel AI SDK

Turn messy docs into a live knowledge graph. Use Cognee with Vercel AI SDK to stream structured data directly into your frontend.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Cognee MCP to Vercel AI SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ingest raw data with Vercel AI SDK

Feed your unstructured text directly into the knowledge base using `cognee_add_data`. Your users won't stare at empty loading spinners while the backend churns through documents. This function bridges the gap between raw input and graph-ready data. It handles the heavy lifting so your app stays responsive during the ingestion phase.

Process connections in the browser

Trigger the `cognee_cognify` tool to map out entities and their relationships. This turns scattered text into a navigable graph that your AI client can actually understand. Everything happens in the background, keeping your UI snappy. Your users get a clear view of how their data points connect in real-time.

Query the graph with Cognee

Use `cognee_search` to pull context-aware answers from your graph. Your Vercel AI SDK components receive these results instantly to update the view without a page refresh. Grab deeper insights with `cognee_get_insights` to show users hidden patterns. It makes the data feel alive instead of just sitting there in a database.

Setup guide

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

Install the MCP client package and point it at the Vinkius endpoint. From there, you just pass the server tools into your generateText calls to start querying your graph.

Yes, the server processes batches in the background. Your frontend just needs to fire the ingest tool and wait for the confirmation promise.

Absolutely. Since it is an MCP server, tool results flow right into your streaming response pipeline. You see the structured data populate as the graph traversal completes.

The tool returns an empty set. You should handle this in your UI logic just like any other API call that comes back dry.

Your documents stay within the secure sandbox provided by Vinkius. We strip PII before creating the graph vectors, ensuring your sensitive text is never exposed to the underlying LLM providers.

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