How to Use the Mem AI (Knowledge Workspace) MCP in OpenAI Agents SDK

Q: Can an OpenAI Agents SDK system handle large search payloads from Mem AI (Knowledge Workspace)?

Avoid using listmems for general conversational tasks because it returns heavy payloads that can bloat context windows. Using this MCP Server allows your agent to run searchmems instead, fetching highly targeted semantic results that fit neatly within your token limits.

Q: What is the fastest way to capture a quick note?

Have your agent trigger the memit shortcut. This MCP tool bypasses complex formatting and instantly drops a raw, automated block of text into your workspace for quick processing.

Build production-grade OpenAI Agents SDK systems that read, write, and search your team's knowledge base in Mem AI without manual setup.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mem AI (Knowledge Workspace) MCP to OpenAI Agents SDK

Create your Vinkius account to connect Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Fast semantic search for OpenAI Agents SDK

Your OpenAI Agents SDK system needs direct access to your Mem AI workspace to answer complex user queries without hallucinating. By exposing `search_mems` directly to your agent, the system queries your entire knowledge base and pulls relevant notes instantly. Before executing a search, the built-in OpenAI guardrails validate the retrieved notes. This ensures your agent only reads authorized Mem documents and doesn't leak sensitive workspace files to the wrong user session.

Let your agent organize knowledge in real-time

During active user sessions, your OpenAI agent can instantly write down key takeaways or action items. It uses `create_mem` to format raw text into markdown notes and immediately drops them into the workspace. To keep things clean, the agent groups these notes by running `create_collection` and `add_mem_to_collection` inside your workspace. This keeps your Mem database organized without manual human intervention.

Edit workspace documents safely via MCP Server

Modifying existing Mem documents requires precision to avoid accidental data loss. Your OpenAI agent first calls `get_mem` to pull the current text, then safely applies updates using `update_mem` instead of overwriting blindly. The OpenAI dashboard logs every single workspace transition and tool call. If an agent tries to execute `delete_mem` on a critical note, your custom guardrail blocks it before the destructive API call even fires.

Setup guide

Set up Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Mem AI (Knowledge Workspace) 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="Mem AI (Knowledge Workspace) Agent",
            instructions="You have access to Mem AI (Knowledge Workspace) 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 Mem.ai. 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 Mem AI (Knowledge Workspace) 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 Mem AI (Knowledge Workspace) MCP in OpenAI Agents SDK

Install the SDK and initialize the streamable HTTP transport pointing to your Vinkius endpoint. Pass this server instance directly inside the `mcp_servers` list when instantiating your Agent to let the model auto-discover all tools instantly.

Avoid using `list_mems` for general conversational tasks because it returns heavy payloads that can bloat context windows. Using this MCP Server allows your agent to run `search_mems` instead, fetching highly targeted semantic results that fit neatly within your token limits.

Define validation hooks directly in Python to inspect parameters before executing tool calls. If your OpenAI agent attempts to modify a protected note using `update_mem`, the SDK blocks the action before sending the request to Vinkius.

Have your agent trigger the `mem_it` shortcut. This MCP tool bypasses complex formatting and instantly drops a raw, automated block of text into your workspace for quick processing.

Every request runs inside an isolated, ephemeral V8 sandbox that destroys itself immediately after execution. Your raw Mems and personal notes remain fully encrypted and are never cached or analyzed by Vinkius.

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