How to Use the CrowdSec MCP in LangChain

Build threat intelligence chains with CrowdSec and LangChain to automatically block malicious IPs.

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 LangChain

Create your Vinkius account to connect CrowdSec to LangChain 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 LangChain

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Chain local decisions in LangChain

The `get_decisions` tool lets your agent query the Local API directly through the MCP Server. You pass an IP address, and the server returns active bans or captchas currently enforced on your infrastructure. ReAct agents take this output and feed it into your next node. If an IP shows up as banned, the chain can trigger a Slack alert or write a firewall rule without human intervention.

Poll streams for autonomous response

Calling `get_decisions_stream` pulls the latest delta of new and deleted security decisions. Your application runs this MCP tool on a cron schedule to keep external systems synced with your local blocklist. LangSmith traces every poll attempt. You track token usage and latency for these repetitive tasks, ensuring your threat intel pipeline runs efficiently in the background.

Check global IP reputation

Using `get_cti_smoke` checks an IP against the global CrowdSec database. The agent receives a reputation score based on signals from thousands of other protected servers. Building this into a LangGraph workflow means you check external reputation before making a local decision. Low reputation triggers a temporary block, buying your team time to investigate the traffic spikes.

Setup guide

Set up CrowdSec MCP in LangChain

Prerequisites

Python 3.10+ installed
langchain-mcp-adapters + langgraph packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies
Run pip install langchain-mcp-adapters langgraph langchain-openai. The MCP adapters package converts MCP tools into native LangChain BaseTool objects.
2

Connect via HTTP transport
Use MultiServerMCPClient with "transport": "http" pointing to your Vinkius endpoint. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Create a ReAct agent
Pass the discovered tools to create_react_agent() from LangGraph. The agent automatically routes CrowdSec tool calls through the MCP protocol.
4

Run with any LLM
Swap ChatOpenAI for ChatAnthropic, ChatGoogleGenerativeAI, or any LangChain-compatible model. The MCP tools work identically across all providers.

agent.py

from langchain_mcp_adapters.client import MultiServerMCPClient
from langgraph.prebuilt import create_react_agent
from langchain_openai import ChatOpenAI

async with MultiServerMCPClient({
    "crowdsec-mcp": {
        "transport": "http",
        "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp",
    }
}) as client:
    tools = client.get_tools()

    agent = create_react_agent(
        ChatOpenAI(model="gpt-4o"),
        tools,
    )
    result = await agent.ainvoke({
        "messages": "List recent CrowdSec transactions"
    })
    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 LangChain

Install the langchain-mcp-adapters package first. Then initialize a MultiServerMCPClient pointing to your Vinkius endpoint and pass the extracted tools to your ReAct agent.

Yes, if you wire the output to a remediation tool. The MCP Server currently reads data via the decision endpoints, so your agent needs a separate module to push new firewall rules.

The tool call fails and returns an error string to the agent. You should build error handling into your chain to retry or fallback to global CTI checks.

Every interaction gets logged automatically. You see exactly which IPs the agent queried and the raw JSON response returned by the server.

Your local IP bans and query histories stay encrypted. Vinkius isolates the connection in a V8 sandbox, meaning LangChain only receives the exact decision data it requests without exposing your underlying network topology.

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