How to Use the CrowdSec MCP in Cursor

Let Cursor query CrowdSec decisions and global IP reputation while you write security middleware.

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 Cursor

Create your Vinkius account to connect CrowdSec to Cursor 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 Cursor

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Pull IP Reputation Mid-Code

The `get_cti_smoke` tool lets Cursor hit the global threat intelligence database while you write application code. If you are building a custom rate limiter, the AI can test it against actual malicious IP profiles instead of making up fake data. You ask the agent in your editor to fetch a known bad IP. It pulls the real smoke score and attack history, then writes the exact validation logic you need to handle that specific threat profile.

Query Local Bans inside Cursor

The `get_decisions` tool exposes your active LAPI blocks directly to your coding environment. You can ask the editor to write a script that syncs your current infrastructure bans with a third-party firewall. The agent reads the live list of blocked subnets and generates working code formatted for your exact data structure. You never have to switch to a terminal to check which IPs are currently restricted.

Code Against Live Threat Streams via MCP Server

By calling the `get_decisions_stream` tool, this MCP Server feeds new and deleted security events straight into your IDE. You can build automation that reacts to fresh bans the second they happen. Tell the agent to write a webhook handler for new blocks. It polls the stream to see the exact JSON payload format CrowdSec uses, then writes a parser that perfectly matches those incoming delta events.

Setup guide

Set up CrowdSec MCP in Cursor

Prerequisites

Cursor installed (macOS, Windows, or Linux)
Active Vinkius subscription with a valid endpoint token

1

Open MCP Settings

Go to Cursor Settings → MCP or open the Command Palette (Cmd+Shift+P / Ctrl+Shift+P) and search for "MCP: Add Server".
2

Add the CrowdSec MCP

Cursor will create or open .cursor/mcp.json in your project root. Paste the JSON snippet on the right. Replace [YOUR_TOKEN_HERE] with your endpoint token from cloud.vinkius.com.
3

Enable Agent mode

Open Composer (Cmd+I / Ctrl+I) and switch to Agent mode using the dropdown at the top. MCP tools are only available in Agent mode.
4

Verify the connection

Ask Cursor something like "List my recent CrowdSec transactions." If the MCP tools are loaded correctly, Cursor will call the CrowdSec tools automatically. You can also check Settings → MCP for a green status indicator.

.cursor/mcp.json

{
  "mcpServers": {
    "crowdsec-mcp": {
      "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    }
  }
}

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 Cursor

Create an mcp.json file in your project root or global settings directory. Add the MCP Server configuration under the mcpServers key. Turn on Agent mode in the chat panel to start querying.

The current toolset only reads data. The agent can fetch global reputation scores and read your local API decisions, but it cannot issue new block commands.

You get to write security tooling using real data. The agent pulls actual malicious IP profiles and live ban lists to test your middleware logic while you are actively typing it.

You need to switch to Agent mode. Standard chat cannot execute external tools, but Agent mode gives the AI permission to hit the LAPI and fetch threat intelligence.

The AI only sees the specific IP addresses you ask it to check and the resulting ban decisions. Your source code and environment variables are never sent to the threat intelligence database.

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