How to Use the Cognee MCP in AutoGen

Q: How do I add Cognee tools to an AutoGen agent?

Install the MCP extension using pip install -U "autogen-extmcp" first. Then, use mcpservertools with your Vinkius HTTP URL and pass the resulting tools list to your AssistantAgent.

Q: How do AutoGen agents handle schema conversion for Cognee?

The McpToolAdapter handles this automatically behind the scenes. It translates the Cognee tool schemas into the format AutoGen agents expect, so you don't have to write custom wrappers.

Let your AutoGen agents debate, analyze, and build custom Cognee knowledge graphs using this 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 Cognee MCP to AutoGen

Create your Vinkius account to connect Cognee 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 Cognee with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Ingest data collaboratively using this MCP Server

`cognee_add_data` writes raw unstructured text into your graph database based on instructions from your AutoGen agents. One agent can gather the raw data while another checks it for errors before passing it to this tool. This cooperative workflow ensures only clean data enters your system. Your agents handle the verification step automatically, reducing database noise and keeping your records accurate.

Debate and construct graph structures with AutoGen

`cognee_cognify` parses your ingested files into an interconnected entity graph with vector embeddings. Your AutoGen agents coordinate this process, debating which relationships are valid before executing the tool. This consensus-driven approach prevents messy, redundant nodes. By discussing the data structure first, your agents build a cleaner, more logical knowledge graph.

Query complex relationships via multi-agent consensus

`cognee_search` queries your knowledge graph using natural language and returns context-rich node paths. Your AutoGen agents use this tool to resolve factual disputes during their internal conversations. This setup turns your graph into a single source of truth. Your agents query the graph, compare results, and deliver a verified answer to the user.

Setup guide

Set up Cognee 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 Cognee 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="Cognee_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

result = await agent.run("List recent Cognee 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="Cognee_assistant",
        model_client=OpenAIChatCompletionClient(model="gpt-4o"),
        workbench=workbench,
    )

    result = await agent.run("List recent Cognee 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 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 AutoGen

Install the MCP extension using `pip install -U "autogen-ext[mcp]"` first. Then, use `mcp_server_tools` with your Vinkius HTTP URL and pass the resulting tools list to your `AssistantAgent`.

Yes, any agent in your group conversation can call this tool to fetch relationship data. This helps the agents resolve debates using factual graph connections instead of hallucinated info.

The `McpToolAdapter` handles this automatically behind the scenes. It translates the Cognee tool schemas into the format AutoGen agents expect, so you don't have to write custom wrappers.

Standard search returns isolated snippets, but Cognee provides connected entity paths. This allows your AutoGen agents to trace complex relationships and make better collective decisions.

Vinkius wraps the execution environment in a zero-trust, ephemeral sandbox. Your unstructured text and entity graphs are isolated from other users and never used for training external models.

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