How to Use the Guru MCP in AutoGen

Q: Can AutoGen agents modify Guru cards?

Yes, they use updateknowledgecard or createknowledgecard. You should configure your agents to only do this after they reach a consensus.

Enable debate between AutoGen agents using Guru knowledge to reach consensus on technical decisions.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Guru MCP to AutoGen

Create your Vinkius account to connect Guru 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 Guru with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Debate Guru data in AutoGen

Your research agent uses `search_knowledge_base` to provide facts for the debate. Other agents challenge these findings to ensure quality. This process filters out bad info before your team commits to a decision. It forces the agents to verify their claims against your wiki.

Update documentation via AutoGen

Once agents reach consensus, they use `update_knowledge_card` to record the result. Your wiki stays updated automatically after every team discussion. This keeps your documentation alive. You don't have to manually edit cards after a project finishes.

Manage team access with Guru MCP Server

Agents can call `list_access_groups` to verify who owns a specific card. This ensures the right people get notified of changes. It adds a layer of governance to your automated workflows. Your system respects your existing organizational hierarchy.

Setup guide

Set up Guru 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 Guru 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="Guru_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

    result = await agent.run("List recent Guru 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 Guru. 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 Guru 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 Guru MCP in AutoGen

They call the available tools during their conversation loop. An agent might search the wiki to support an argument during a debate.

Yes, they use `update_knowledge_card` or `create_knowledge_card`. You should configure your agents to only do this after they reach a consensus.

You provide the tool list to your AssistantAgent constructor. The adapter handles the rest of the communication automatically.

They help organize the knowledge space. Agents can list boards first to narrow down their search, which keeps the conversation focused.

The server functions within a V8 sandbox, ensuring no code leaks between agents. It only touches your knowledge card content, never your team's internal credentials.

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