How to Use the CrowdSec MCP in AutoGen

Q: How do I load CrowdSec tools into an AutoGen swarm?

Use the autogen-ext package and initialize mcpservertools. Pass the resulting list into your AssistantAgent constructor to grant it MCP access.

Give your AutoGen agents access to CrowdSec threat intel to debate and resolve security alerts.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect CrowdSec MCP to AutoGen

Create your Vinkius account to connect CrowdSec 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 CrowdSec with AutoGen

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Resolve alerts with AutoGen

Triggering `get_cti_smoke` fetches the global reputation of a suspicious IP. The tool returns known attack vectors and background context from the wider community. A security agent reviews this score while an operations agent checks server logs. They debate whether to drop traffic completely or just issue a captcha, reaching a consensus before taking action.

Audit local enforcement rules

The `get_decisions` tool asks the Local API for current active blocks. It requires an IP or range and outputs the specific rules currently applied to that target. Multiple agents can analyze these active rules against company policy. If an agent notices a critical internal IP got banned by mistake, it alerts the human operator to override the decision.

Monitor threat streams continuously

Calling `get_decisions_stream` checks for delta updates in your ban lists via the MCP Server. The endpoint replies with an array of newly blocked IPs and those that just aged out. You assign a watcher agent to run this MCP tool on a loop. When new threats appear, it broadcasts the update to the chat room, prompting the rest of the swarm to investigate the root cause.

Setup guide

Set up CrowdSec 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 CrowdSec 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="CrowdSec_assistant",
    model_client=OpenAIChatCompletionClient(model="gpt-4o"),
    tools=tools,
)

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

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

Use the autogen-ext package and initialize mcp_server_tools. Pass the resulting list into your AssistantAgent constructor to grant it MCP access.

Yes. The Vinkius endpoint handles concurrent requests natively. Different agents can query different IPs at the exact same time without blocking each other.

The system prompt dictates their behavior. If you instruct the security persona to verify all external connections, it will call the tool autonomously during the conversation.

The tools return structured JSON containing threat scores, categories, and expiration timestamps. The adapter automatically converts this into text for the LLM to read.

Network topologies and local API endpoints remain hidden behind the V8 Isolate Sandbox. AutoGen only transmits the specific IP strings you ask it to investigate, and the MCP Server retains zero logs of your queries.

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