4,500+ servers built on MCP Fusion
Vinkius
CrowdSec logo
Vinkius
Claude Desktop logo

How to Use the CrowdSec MCP in Claude

Give Claude Desktop direct access to CrowdSec threat intelligence to investigate IPs and active bans right in your chat window.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

CrowdSec MCP on Cursor AI Code Editor MCP Client CrowdSec MCP on Claude Desktop App MCP Integration CrowdSec MCP on OpenAI Agents SDK MCP Compatible CrowdSec MCP on Visual Studio Code MCP Extension Client CrowdSec MCP on GitHub Copilot AI Agent MCP Integration CrowdSec MCP on Google Gemini AI MCP Integration CrowdSec MCP on Lovable AI Development MCP Client CrowdSec MCP on Mistral AI Agents MCP Compatible CrowdSec MCP on Amazon AWS Bedrock MCP Support
MCP Servers - Free for Subscribers
Claude Desktop

Connect CrowdSec MCP to Claude Desktop

Create your Vinkius account to connect CrowdSec to Claude Desktop 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

Investigate Suspicious IPs via Claude Desktop

The `get_cti_smoke` tool lets Claude Desktop pull the global reputation for any IP address instantly. When your logs show weird traffic spikes, you do not have to leave the chat to figure out if the source is a known bad actor. You just paste the IP into your prompt. The agent hits the CrowdSec CTI database, reads the smoke score, and tells you exactly what kind of attacks that address is famous for.

Read Active LAPI Decisions

Using the `get_decisions` tool, your AI client queries your Local API to see exactly who is blocked right now. This means you can ask Claude to summarize the current firewall state without touching a command line. The server pulls down the active list of bans and captchas applied to your infrastructure. You get a plain English breakdown of which subnets are locked out and why the security engine flagged them.

Monitor Threat Streams with this MCP Server

The `get_decisions_stream` tool turns this MCP Server into a live monitor for new and deleted security rules. Claude can poll the local engine to see what changed in the last five minutes. Instead of digging through raw logs, you ask the agent what IPs just got banned. It fetches the latest delta from the stream and formats the blocklist updates for your incident report.

Setup guide

Set up CrowdSec MCP in Claude Web or Desktop

  1. 1

    Open Claude Settings

    Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.

  2. 2

    Add Custom Connector

    Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL: https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. For OAuth-protected servers, expand Advanced settings to add credentials.

  3. 3

    Start a conversation

    Open a new chat. The CrowdSec MCP tools are available immediately — no restart needed.

Endpoint URL

https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp

No configuration file needed — paste the URL directly in the Claude web interface.

Available on Free (1 connector), Pro, Max, Team, and Enterprise plans.

Why Choose Vinkius

Vinkius connects your tools to AI with real-time monitoring and automatic cost savings — all from one dashboard.

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 Claude Desktop

Open your claude_desktop_config.json file from the developer settings. Add the server details under the mcpServers array and restart the app. You can also paste the remote URL into Claude Web's integrations tab.
No. This integration is read-only. The tools query the CTI database and your local API for decisions, but they do not write new rules or delete existing bans.
It puts global threat intelligence right where you are writing your post-mortem. You paste an IP into the chat, and the agent pulls its entire attack history and current ban status.
The local API holds your specific infrastructure's active decisions. Connecting this MCP Server to it allows the agent to see exactly which addresses your firewalls are currently blocking.
The only data moving through this connection are IP addresses and ban decisions. The server never reads your application payloads, user data, or full network packets.

Start using the CrowdSec MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Built & Managed by Vinkius 30s setup 3 tools

We've already built the connector for CrowdSec. Just plug in your AI agents and start using Vinkius.

No hosting. No infrastructure. No complex setup.
All 3 tools are live and waiting. You're up and running in seconds.

Claude Claude
ChatGPT ChatGPT
Cursor Cursor
Gemini Gemini
Windsurf Windsurf
VS Code VS Code
JetBrains JetBrains
Vercel Vercel
+ other MCP clients

Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.

Zero hosting required Full MCP catalog included Enterprise-grade security Auto-updated by Vinkius

Built, hosted, and secured by Vinkius. You just connect and go.