How to Use the CrowdSec MCP in Vercel AI SDK

Q: Can Vercel AI SDK handle live streaming of CrowdSec decisions?

Yes. By calling getdecisionsstream, your application can pipe real-time IP ban updates directly into the UI, bypassing the need for manual polling loops.

Feed real-time CrowdSec threat intelligence straight into your Vercel AI SDK streaming interface using this lightweight MCP Server.

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 Vercel AI SDK

Create your Vinkius account to connect CrowdSec to Vercel AI SDK 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 Vercel AI SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Stream IP reputation checks live to your frontend

The `get_cti_smoke` tool lets your AI client check global IP reputation scores instantly. By connecting this MCP Server to your web interface, your application can display live risk ratings as users interact with your network endpoints. Because you are building on the Vercel AI SDK, you do not have to wait for the entire security check to finish before rendering. The reputation data streams directly into your UI components, keeping the interface snappy and responsive while background security checks run.

Active threat blocking via Vercel AI SDK

The `get_decisions` tool queries your local CrowdSec LAPI to see if an incoming IP already has active blocks against it. Your agent can read these decisions and instantly decide whether to restrict access or flag a session. This integration works perfectly within Edge Functions. You get low-latency evaluations that feed directly into your frontend routing logic, allowing your application to block malicious actors before they can load heavy page assets.

Live security feeds in your Next.js dashboard

The `get_decisions_stream` tool polls your local API for new and deleted IP bans. This feed keeps your agent updated on what IPs are currently banned or cleared in your environment. Instead of building complex WebSockets, you let this MCP Server handle the stream. Your AI client reads the live updates and pushes them directly to your security dashboard, letting admins see active blocks update in real time.

Setup guide

Set up CrowdSec MCP in Vercel AI SDK

Prerequisites

Node.js 18+ and a TypeScript project
ai + @modelcontextprotocol/sdk packages
Active Vinkius subscription with a valid endpoint token

1

Install dependencies

Run npm install ai @modelcontextprotocol/sdk plus your preferred model provider (e.g. @ai-sdk/openai).
2

Create the Streamable HTTP transport

Use StreamableHTTPClientTransport with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com.
3

Discover and use tools

Call mcpClient.tools() to auto-discover all CrowdSec tools. Pass them directly to generateText() or streamText() — no manual schema definitions needed.
4

Works with any model provider

Swap openai("gpt-4o") for any AI SDK provider — Anthropic, Google, Mistral. The MCP tools work identically across all supported models.

index.ts

import { experimental_createMCPClient as createMCPClient } from "ai";
import { StreamableHTTPClientTransport } from "@modelcontextprotocol/sdk/client/streamableHttp";
import { generateText } from "ai";
import { openai } from "@ai-sdk/openai";

const transport = new StreamableHTTPClientTransport(
  new URL("https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")
);

const mcpClient = await createMCPClient({ transport });
const tools = await mcpClient.tools();

const { text } = await generateText({
  model: openai("gpt-4o"),
  tools,
  prompt: "List recent CrowdSec transactions",
});

console.log(text);
await mcpClient.close();

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 Vercel AI SDK

Run npm install ai @ai-sdk/mcp in your project. Initialize the client using createMCPClient with your Vinkius HTTP endpoint, then pass the tools directly into streamText.

Yes. By calling get_decisions_stream, your application can pipe real-time IP ban updates directly into the UI, bypassing the need for manual polling loops.

Yes, you need access to either a local CrowdSec LAPI instance to fetch decisions or the global CTI network. The server connects your Vercel AI SDK setup directly to these APIs via Vinkius.

Always call mcpClient.close() once your AI client finishes processing the security tools. This prevents open HTTP connections from hanging in your serverless or edge environments.

Your IP addresses and local block decisions are processed within an isolated V8 sandbox on Vinkius. No reputation data is stored permanently on our servers, and all API calls to your CrowdSec LAPI are encrypted in transit.

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