How to Use the Intruder MCP in Pydantic AI

Q: How do I initialize the Intruder MCP Server with Pydantic AI?

Install the slim package with pip install "pydantic-ai-slimmcp" and instantiate the MCP server toolset with your server's HTTP endpoint. Pass the toolset directly to your Agent to expose tools like listissues and listtargets with automatic runtime validation.

Q: Can I use Pydantic AI to enforce schema checks on Intruder scans?

Yes, when your agent calls listscans or getscan, Pydantic AI validates the structure of the returned scan metadata. This guarantees that parameters like timestamps, scan IDs, and target counts conform to your expected data types.

Guarantee type-safe vulnerability management by validating Intruder security data at runtime using 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 Intruder MCP to Pydantic AI

Create your Vinkius account to connect Intruder 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 Intruder with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate vulnerability payloads using Pydantic AI

`list_issues` fetches active security flaws, and Pydantic AI immediately validates the severity levels, titles, and IDs against strict Python type models. If the API returns unexpected data, the framework fails loudly before your code can process a bad payload. By registering this MCP Server via `MCPToolset`, your agent gains type-safe access to your entire security posture. The agent calls `get_issue` to extract remediation details, ensuring every field matches your exact schema before triggering downstream workflows.

Run strict audits on cloud targets and integrations

`list_targets` returns your active infrastructure assets, which are validated at runtime to ensure target IDs and types conform to your security policies. The agent cross-references these with `list_cloud_integrations` to verify that every cloud account is accounted for. This setup prevents silent failures in your security pipelines. The agent uses `get_target` to fetch specific metadata, guaranteeing that your monitoring scripts never run against malformed target records.

Track scan execution with guaranteed schema compliance

`list_scans` outputs your historical scan data, which your agent parses to verify that security checks are running on schedule. The agent uses `get_scan` to pull findings, validating that the scan duration and target counts are positive integers. This integration lets your Pydantic AI agent query `list_licences` and `list_teams` to audit organizational access. Because every response is validated, your automated compliance reports are guaranteed to be structurally correct.

Setup guide

Set up Intruder 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": {
        "intruder-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install the slim package with `pip install "pydantic-ai-slim[mcp]"` and instantiate the MCP server toolset with your server's HTTP endpoint. Pass the toolset directly to your `Agent` to expose tools like `list_issues` and `list_targets` with automatic runtime validation.

The framework will raise a validation error immediately at runtime, preventing your agent from executing actions based on corrupted data. This ensures that tools like `get_issue` or `get_scan` never pass malformed payloads to your remediation scripts.

Yes, when your agent calls `list_scans` or `get_scan`, Pydantic AI validates the structure of the returned scan metadata. This guarantees that parameters like timestamps, scan IDs, and target counts conform to your expected data types.

Yes, the MCP server integration supports both Streamable HTTP and SSE transports. This allows your agent to communicate with the externally running server regardless of your network architecture.

Your API keys and target data are handled securely through the Vinkius gateway, which manages authentication using a single-token endpoint. Pydantic AI validates the incoming target metadata locally, ensuring raw security credentials are never exposed or logged.

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