How to Use the CrowdSec MCP in Pydantic AI

Q: What happens if the CrowdSec API changes unexpectedly when using Pydantic AI?

Your agent will fail loudly with a ValidationError. This is a feature, not a bug. It prevents your agent from acting on corrupted or unexpected data, which is critical for security automation with CrowdSec.

Q: How do I connect the CrowdSec MCP Server in Pydantic AI?

It's straightforward. You create an MCPToolset instance with the Vinkius server URL and pass it to your Agent's toolsets list. Pydantic AI handles the rest.

Add type-safe CrowdSec threat intelligence to any LLM with Pydantic AI. Get validated data structures, not messy strings.

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 Pydantic AI

Create your Vinkius account to connect CrowdSec to Pydantic AI 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 Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Validated IP Reputation Data

The `get_cti_smoke` tool lets your agent check an IP's reputation. When you use it with Pydantic AI, the response is automatically parsed and validated against a Pydantic model. You get structured data you can actually work with. If the CrowdSec API ever changes or returns something unexpected, your code will raise a `ValidationError` immediately. This means no silent data corruption. You can trust that the IP reputation data your agent is using is exactly what you expect it to be.

Query Decisions with Full Type Safety

Use `get_decisions` to have your agent query your local CrowdSec instance for active security blocks. Pydantic AI ensures the list of decisions your agent receives is a properly typed Python object. You can iterate over it without guesswork or defensive code. This makes your agent's logic much more reliable. You don't need to write `try/except` blocks to handle malformed API responses from this MCP Server. If the data is bad, your agent stops instead of making a bad decision.

Build a Reliable Stream of Security Events

The `get_decisions_stream` tool pushes new and deleted decisions to your agent as they happen. Each event that comes through the stream is validated by Pydantic AI before your agent even sees it. This is critical for building dependable security automation. Your agent can react to real-time events, confident that every piece of data conforms to your Pydantic models. It's the key to building automation that doesn't break silently.

Setup guide

Set up CrowdSec MCP in Pydantic AI

Prerequisites

Python 3.10+ installed
pydantic-ai-slim[fastmcp] package
Active Vinkius subscription with a valid endpoint token

1

Install Pydantic AI with FastMCP
Run pip install "pydantic-ai-slim[fastmcp]". The FastMCP toolset replaces the deprecated MCPServerHTTP class with full protocol support.
2

Configure the FastMCPToolset
Pass a JSON-style config dict to FastMCPToolset with your Vinkius URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. Supports Streamable HTTP, SSE, and Stdio transports.
3

Create and run your agent
Pass the toolset to Agent(toolsets=[toolset]) and call agent.run(). Swap openai:gpt-4o for any supported model — Anthropic, Google, Mistral, or Groq.

agent.py

from pydantic_ai import Agent
from pydantic_ai.toolsets.fastmcp import FastMCPToolset

toolset = FastMCPToolset({
    "mcpServers": {
        "crowdsec-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

agent = Agent(
    "openai:gpt-4o",
    toolsets=[toolset],
    system_prompt="You have access to CrowdSec tools.",
)

result = await agent.run("List recent CrowdSec transactions")
print(result.output)

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 Pydantic AI

Pydantic AI validates every API response from the CrowdSec MCP Server against a Pydantic model. If the data, like an IP's reputation, doesn't match the expected types and structure, it throws an error instead of letting your agent use bad data.

Yes. Pydantic AI is model-agnostic. You can connect this MCP Server and use the CrowdSec tools with agents powered by OpenAI, Anthropic, or even a model running on your own machine.

Your agent will fail loudly with a `ValidationError`. This is a feature, not a bug. It prevents your agent from acting on corrupted or unexpected data, which is critical for security automation with CrowdSec.

It's straightforward. You create an `MCPToolset` instance with the Vinkius server URL and pass it to your `Agent`'s `toolsets` list. Pydantic AI handles the rest.

Your agent sends only the IP addresses it needs to check. This MCP Server runs in a secure, isolated V8 sandbox for each request. Vinkius does not log or retain any of the IP addresses you process.

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