How to Use the Beagle Security MCP in Pydantic AI

Q: What's the setup process for Beagle Security and Pydantic AI?

It's minimal. First, pip install "pydantic-ai-slimmcp". Then, create an MCPToolset instance, passing it your Vinkius URL for the Beagle Security server. Add that toolset to your Agent's toolsets list.

Add type-safe security automation to your Python app. Run Beagle Security tests and get validated responses with Pydantic AI.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Beagle Security MCP to Pydantic AI

Create your Vinkius account to connect Beagle Security 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 Beagle Security with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Type-Safe Security Results

This MCP Server lets your agent pull security test data that's guaranteed to match your Pydantic models. When your agent calls `get_test_results` or `get_vulnerabilities`, the JSON response from Beagle Security is parsed and validated on the spot. If Beagle's API ever changes or returns an unexpected data structure, Pydantic AI will raise a `ValidationError` immediately. You don't have to worry about your agent silently failing or working with corrupted data. Your code either gets clean data or a clear error.

Reliably Control Security Tests

You can build reliable automation around starting and stopping scans. Your Pydantic AI agent can use `start_test` to kick off a new scan, and the toolset ensures the parameters are correct. You can also build polling logic that is much safer. The agent can call `get_test_status` in a loop, and you know the response ('RUNNING', 'COMPLETED', etc.) will always be one of the expected values because it's validated. This prevents bugs from typos or API changes.

A Pydantic AI Ready MCP Server

Your agent can safely explore your Beagle Security account. It can call `list_projects` and `list_applications` to get lists of resources, with Pydantic AI ensuring each item in the list conforms to your defined schema. This MCP Server works with any LLM you plug into Pydantic AI, whether it's from OpenAI, Anthropic, or a local model. The toolset is independent of the brain, giving you type-safe tool use everywhere. You can even fetch account info with `get_user_profile`.

Setup guide

Set up Beagle Security 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": {
        "beagle-security-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Beagle Security 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 Beagle Security. 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 Beagle Security 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 Beagle Security MCP in Pydantic AI

It makes them impossible to ignore. If the Beagle Security API returns data that doesn't match the expected Pydantic model for a tool like `get_vulnerabilities`, Pydantic AI throws a `ValidationError`. This is much better than your agent getting `None` and proceeding incorrectly.

Yes. Pydantic AI is model-agnostic. You configure your agent with the LLM of your choice, then add the Beagle Security MCP toolset. The tool-calling and response validation work the same way for local models as they do for commercial APIs.

It's minimal. First, `pip install "pydantic-ai-slim[mcp]"`. Then, create an `MCPToolset` instance, passing it your Vinkius URL for the Beagle Security server. Add that toolset to your `Agent`'s `toolsets` list.

The overhead is negligible. Pydantic is highly optimized for this kind of data parsing and validation. The time it takes to validate a response from `get_test_results` is tiny compared to the network latency of the API call itself.

The server handles your Beagle Security account data, such as project and application details, test IDs, and the contents of vulnerability reports. This data passes through Vinkius's secure, ephemeral infrastructure, which is designed to process requests without storing your information.

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