How to Use the Cerbos MCP in AutoGen

Q: Can AutoGen agents negotiate using Cerbos?

Yes, they can debate the results of authzenevaluations during their conversation. If one agent denies access, the other can propose a different approach.

Let your AutoGen agents debate and verify security decisions using the Cerbos 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 Cerbos MCP to AutoGen

Create your Vinkius account to connect Cerbos 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 Cerbos with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Consensus-based auth in AutoGen

Assign the `authzen_evaluation` tool to a security agent within your AutoGen team. Other agents can propose actions, and the security agent will force a consensus check before moving forward. It creates a layer of friction where risky actions get flagged. The agents must agree on the authorization outcome before the task proceeds.

Debating permission plans in AutoGen

Use `plan_resources` to provide your agents with a list of allowed resources to discuss. The agents can compare these plans against their goals and negotiate the most efficient path. It removes the ambiguity of who is allowed to do what. The agents debate the constraints returned by Cerbos until they reach a valid plan.

Managing Cerbos tools in AutoGen teams

The McpToolAdapter automatically converts your Cerbos tools for use in any AssistantAgent. You define the team, and the agents handle the tool calls as part of their conversation flow. It keeps your security logic separate from your business logic. Your agents just see a list of tools they can use to verify their next move.

Setup guide

Set up Cerbos 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 Cerbos 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="Cerbos_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Pass the tools list generated by the MCP adapter to your AssistantAgent. The agents will automatically know how to invoke the evaluation functions.

Yes, they can debate the results of `authzen_evaluations` during their conversation. If one agent denies access, the other can propose a different approach.

It integrates directly into the conversation loop. You can have a dedicated security agent call these tools to validate the team's progress.

Yes, the conversation history captures every tool call and its output. You can audit exactly why an agent decided to block or permit an action.

We keep all evaluation data in memory during the conversation. Your authorization policies and resource identifiers are never logged or stored by the server.

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