How to Use the Mem0 MCP in OpenAI Agents SDK

Q: How do I register the Mem0 MCP Server in my OpenAI Agents SDK pipeline?

You initialize the server via MCPServerStreamableHttp and pass it directly to the Agent constructor. The SDK automatically discovers the four memory tools.

Q: How does Mem0 handle data privacy for user memories stored via this SDK?

Every structured fact and user preference sent via addmemory is stored in a secure, isolated sandbox. You control the encryption keys, ensuring that sensitive user data remains protected and compliant with your enterprise standards.

Give your OpenAI Agents SDK production MCP workflows persistent recall that survives agent handoffs and matches your safety guardrails.

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 OpenAI Agents SDK

Create your Vinkius account to connect Mem0 to OpenAI Agents 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Persistent OpenAI Agents SDK context across handoffs

The `add_memory` tool lets your OpenAI Agents SDK write structured user facts to Mem0 during a live session, meaning when you hand off a conversation from a triage agent to a billing agent, the context doesn't vanish. Your receiving agent queries the database immediately to understand the user's past choices. You don't have to pass massive system prompts down the chain anymore. By letting the active agent run `search_memories`, you fetch only the relevant facts, cutting down token overhead and keeping your MCP tracing dashboard clean.

Guardrail-validated memory pruning

The `delete_memory` tool integrates directly into the OpenAI Agents SDK safety loop to ensure users can wipe their stored preferences instantly. If a user asks to clear their data, your agent executes this tool to remove the specific memory ID without human intervention. Because the SDK enforces strict validation before calling external MCP tools, you can set parameters that prevent the agent from accidentally wiping the wrong memory records. This keeps your user profile database clean and compliant.

On-demand profile building for agent routing

The `get_memories` tool retrieves the complete list of stored facts for any specific user ID so your OpenAI Agents SDK can route the conversation based on user history. When the memory list shows a preference for advanced technical support, the SDK routes the user to the senior engineering agent immediately. Running this check at the start of a session lets you boot up the agent with pre-loaded user context. You avoid making the user repeat their preferences, creating a continuous conversational thread.

Setup guide

Set up Mem0 MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Mem0 tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Mem0 tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Mem0 tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Mem0 Agent",
            instructions="You have access to Mem0 tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

It keeps your context window small. Instead of dumping entire chat histories into the OpenAI Agents SDK prompt, you use `search_memories` to pull only the specific facts relevant to the current user query.

Yes, that is exactly what it is for. When one agent hands off to another, the receiving agent runs `get_memories` using the active user ID to instantly inherit all stored context.

You initialize the server via `MCPServerStreamableHttp` and pass it directly to the `Agent` constructor. The SDK automatically discovers the four memory tools.

The OpenAI Agents SDK guardrails validate the arguments before executing the tool. If the model attempts to pass an invalid memory ID to `delete_memory`, the SDK blocks the call.

Every structured fact and user preference sent via `add_memory` is stored in a secure, isolated sandbox. You control the encryption keys, ensuring that sensitive user data remains protected and compliant with your enterprise standards.

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