How to Use the CrowdSec MCP in Google ADK

Q: How do I add CrowdSec tools to my Google ADK agent?

Instantiate an McpToolset with the server URL provided by Vinkius. Then, pass that toolset into the LlmAgent constructor's tools list. The agent will then have access to all the CrowdSec functions.

Q: How does the Google ADK handle real-time alerts from CrowdSec?

You'd use the getdecisionsstream tool. Your agent can listen to this stream and, when a new decision from CrowdSec arrives, trigger another action in your Google Cloud environment, like publishing a message to Pub/Sub.

Q: What if I only want my Google ADK agent to use one of the CrowdSec tools?

The McpToolset in the Google ADK has a toolnames filter. You can use it to expose only specific tools, like getctismoke, and hide the others from your agent.

Connect Google ADK agents to CrowdSec for threat intelligence that works with your data in BigQuery and Google Cloud.

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 Google ADK

Create your Vinkius account to connect CrowdSec to Google ADK 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 Google ADK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enrich BigQuery Data with IP Intel

Your ADK agent can use `get_cti_smoke` to check IP addresses against the CrowdSec CTI. This is perfect for enriching security logs you already have stored in BigQuery. Just have your agent read IPs from a table and write the reputation data back. With Gemini's long context window, an agent can process thousands of IPs from a BigQuery result set in a single session. It can analyze the results from CrowdSec, spot patterns, and summarize the threat landscape for an entire dataset.

Act on Your Local CrowdSec LAPI

The `get_decisions` tool connects your Google ADK agent directly to your own CrowdSec instance's decisions. Your agent can check if a specific IP is currently blocked by your firewall rules. This lets you build automation that respects your existing security setup. Because the agent is running on Google Cloud, it can take the output from `get_decisions` and act on it within your GCP environment. For example, it could update a firewall rule in VPC or trigger a Cloud Function based on a new decision.

Build Real-Time Monitors with this MCP Server

The `get_decisions_stream` tool provides a continuous feed of security events from your CrowdSec LAPI. A Google ADK agent can subscribe to this stream and get updates in real time. You'll know the second a new IP is blocked or a decision expires. You can use this to build a monitoring system that writes directly to BigQuery or Pub/Sub. The agent acts as a bridge, turning the CrowdSec event stream into a data source for your other Google Cloud services. This MCP Server makes that connection simple.

Setup guide

Set up CrowdSec MCP in Google ADK

Prerequisites

Python 3.10+ installed
google-adk package (pip install google-adk)
Active Vinkius subscription with a valid endpoint token

1

Install Google ADK

Run pip install google-adk to install the Agent Development Kit. MCP support is included via the McpToolset class.
2

Connect via SSE transport

Use McpToolset.from_server() with SseServerParams pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create an LlmAgent

Pass the returned mcp_tools list directly to LlmAgent(tools=mcp_tools). The ADK maps each MCP tool to a native Gemini function call — no manual schema definitions required.
4

Run with any Gemini model

The agent works with any Gemini model (gemini-2.0-flash, gemini-2.5-pro, etc.). Copy the full example on the right to get started with CrowdSec tools in your ADK agent.

agent.py

from google.adk.agents import LlmAgent
from google.adk.tools.mcp_tool.mcp_toolset import McpToolset
from google.adk.tools.mcp_tool.mcp_session_manager import SseServerParams

# Connect to the MCP via SSE
mcp_tools, exit_stack = await McpToolset.from_server(
    connection_params=SseServerParams(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    )
)

# Create your agent with auto-discovered tools
agent = LlmAgent(
    name="CrowdSec_agent",
    model="gemini-2.0-flash",
    instruction="You have access to CrowdSec tools via MCP.",
    tools=mcp_tools,
)

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 Google ADK

Instantiate an `McpToolset` with the server URL provided by Vinkius. Then, pass that toolset into the `LlmAgent` constructor's `tools` list. The agent will then have access to all the CrowdSec functions.

Absolutely. Your agent can read a log file, extract the IP addresses, and then call `get_cti_smoke` on each one. With Gemini's large context, it can then summarize the findings for the entire file.

You'd use the `get_decisions_stream` tool. Your agent can listen to this stream and, when a new decision from CrowdSec arrives, trigger another action in your Google Cloud environment, like publishing a message to Pub/Sub.

The `McpToolset` in the Google ADK has a `tool_names` filter. You can use it to expose only specific tools, like `get_cti_smoke`, and hide the others from your agent.

The only data transmitted is the IP address for each query. Vinkius processes these requests in a zero-trust, ephemeral sandbox. Nothing is logged or stored, so your query data remains private.

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