How to Use the Mem AI (Knowledge Workspace) MCP in AutoGen

Q: Can AutoGen agents collaboratively edit a Mem AI (Knowledge Workspace) note?

Yes. One agent can retrieve the note using getmem, propose changes in the chat, and another agent can execute the update via updatemem once consensus is reached.

Q: How do AutoGen agents search my Mem AI (Knowledge Workspace)?

Agents can call searchmems to run semantic searches across your workspace. They can share the search results in their conversation to coordinate their next actions.

Let your AutoGen agents debate, organize, and update your Mem AI workspace through consensus-driven conversations.

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 AutoGen

Create your Vinkius account to connect Mem AI (Knowledge Workspace) to AutoGen 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 AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-Driven Workspace Organization

This MCP Server enables cooperative AutoGen agents to manage your notes using `create_mem` and `add_mem_to_collection`. One agent can draft a summary of a task, while a second agent reviews it for accuracy before committing it to your workspace. This prevents messy or incomplete notes from cluttering your account. The agents can discuss how to categorize new information before running `create_collection`. Once they agree on a category, they use the tools to organize the notes. This collaborative approach ensures your workspace remains structured and easy to navigate.

Debate and Verify Workspace Context

This MCP toolset allows AutoGen agents to retrieve and verify information using `get_mem` and `search_mems`. When a user asks a complex question, different agents can search your workspace, compare notes, and debate the findings. This leads to more reliable decisions based on actual documented facts. If an agent finds conflicting information, it can call `list_collection_mems` to gather more context. The agents then negotiate which note is correct before presenting the final answer. This eliminates errors caused by outdated or duplicate documents.

Automate Workspace Maintenance via AutoGen

This MCP Server gives your agent groups the ability to clean up outdated information using `update_mem` and `delete_mem`. A maintenance agent can flag old notes, while a supervisor agent approves their deletion or modification. This keeps your workspace accurate without requiring manual curation. The agents run `list_collections` to audit your existing structure and identify empty or redundant groups. They can update note content natively by swapping strings to keep everything current. All of this happens autonomously through agent-to-agent conversation.

Setup guide

Set up Mem AI (Knowledge Workspace) MCP in AutoGen

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] package
Active Vinkius subscription with a valid endpoint token

1

Install AutoGen with MCP
Run pip install "autogen-ext[mcp]" autogen-agentchat. The MCP extension includes mcp_server_tools for stateless tool access.
2

Fetch tools from the MCP
Call mcp_server_tools(SseServerParams(url=...)) with your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Run your agent
Pass the tools to AssistantAgent and call agent.run(). The agent invokes Mem AI (Knowledge Workspace) tools and returns structured results.

agent.py

from autogen_ext.tools.mcp import SseServerParams, mcp_server_tools
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

tools = await mcp_server_tools(server_params)

agent = AssistantAgent(
    name="Mem AI (Knowledge Workspace)_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Mem AI (Knowledge Workspace) data")
print(result.messages[-1].content)

Get your connection token →

Prerequisites

Python 3.10+ installed
autogen-ext[mcp] + autogen-agentchat
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Same packages as above. McpWorkbench is ideal when your agent needs stateful sessions across multiple tool calls.
2

Use McpWorkbench as context manager
Wrap your agent in async with McpWorkbench(...) to maintain shared state and resources. The workbench manages the full MCP session lifecycle.
3

Run with workbench
Pass workbench=workbench to your agent. State is preserved across multiple tool calls within the same session.

agent.py

from autogen_ext.tools.mcp import McpWorkbench, SseServerParams
from autogen_agentchat.agents import AssistantAgent
from autogen_ext.models.openai import OpenAIChatCompletionClient

server_params = SseServerParams(
    url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
)

async with McpWorkbench(server_params) as workbench:
    agent = AssistantAgent(
        name="Mem AI (Knowledge Workspace)_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Mem AI (Knowledge Workspace) data")
    print(result.messages[-1].content)

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 AutoGen

Use the AutoGen MCP extension with your server URL to get the tools. Pass the resulting list directly to your AssistantAgent constructor.

Yes. One agent can retrieve the note using `get_mem`, propose changes in the chat, and another agent can execute the update via `update_mem` once consensus is reached.

Agents can call `search_mems` to run semantic searches across your workspace. They can share the search results in their conversation to coordinate their next actions.

AutoGen's conversation flow ensures agents take turns. One agent will complete its `update_mem` call before the next agent processes the updated content.

All MCP tool calls run through a secure zero-trust sandbox. Your API keys and raw text notes are never exposed to the agents or external networks during the process.

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