How to Use the Mem0 MCP in Vercel AI SDK

Q: Can I use Mem0 to build a user profile in Vercel AI SDK?

You can. Use getmemories to pull the full history of a user and feed that into your agent's system prompt to build a complete profile.

Q: What happens if I need to clear a specific Mem0 fact in Vercel AI SDK?

Call deletememory with the specific memory ID. The record is removed from the database immediately.

Give your Vercel AI SDK apps long-term memory. Store and recall user preferences instantly with the Mem0 MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mem0 MCP to Vercel AI SDK

Create your Vinkius account to connect Mem0 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 Mem0 with Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Persistent user context in Vercel AI SDK

Your AI client needs to remember user preferences across sessions. The `add_memory` tool pushes structured facts into your database, ensuring the state persists beyond the current request. This keeps your application context clean. You avoid passing massive system prompts by using `get_memories` to fetch only the relevant details needed for the current task.

Semantic recall for live UI streams

The `search_memories` tool lets your agent find specific user history in milliseconds. It returns results ranked by relevance, which allows the AI to provide accurate, personalized responses in your streaming UI. Since this works with Vercel AI SDK's streaming capabilities, the retrieved context hits the model before the first token appears. It feels like the AI remembers the user from day one.

Granular memory management

You maintain full control over what the AI keeps. The `delete_memory` tool lets you prune outdated or incorrect facts from the user profile immediately. This prevents the context window from filling with junk data. You define the lifecycle of the information so your agent stays focused and useful.

Setup guide

Set up Mem0 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 Mem0 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 Mem0 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 Mem0. 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 Mem0 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 Mem0 MCP in Vercel AI SDK

Install the MCP client package and initialize the connection with your server endpoint. Once linked, pass the Mem0 tools into your `generateText` or `streamText` function calls.

Yes. The transport layer is compatible with edge runtimes. It keeps your latency low enough for real-time user interaction.

You can. Use `get_memories` to pull the full history of a user and feed that into your agent's system prompt to build a complete profile.

The server only touches the specific facts you send via the tool calls. You control the scope of the data stored for each unique user ID.

Call `delete_memory` with the specific memory ID. The record is removed from the database immediately.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.