How to Use the Have I Been Pwned MCP in Pydantic AI

Enforce strict security types in Pydantic AI using the Have I Been Pwned MCP Server for reliable credential validation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Have I Been Pwned MCP to Pydantic AI

Create your Vinkius account to connect Have I Been Pwned 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 Have I Been Pwned with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe password checking

By using `check_password_safety`, you ensure the agent receives a validated response structure. Pydantic AI rejects any malformed output, so you never handle corrupt data. This is the safest way to implement password checks. If the service returns a weird payload, your agent fails immediately instead of proceeding with bad information.

Validate breach data with Pydantic models

The tool `get_breach_details` maps directly to your predefined Pydantic models. You define the schema, and the agent populates it with verified data from HIBP. It removes the risk of hallucinated fields. You get a clean, typed object that you can immediately store or use for logic gates in your Pydantic AI workflow.

Search pastes with strict validation

Use `search_account_pastes` to retrieve external leaks with full type checking. Every response from the MCP Server is checked against your model definition. This prevents runtime errors in your Pydantic AI agents. You know exactly what the data looks like before your code touches it.

Setup guide

Set up Have I Been Pwned 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": {
        "have-i-been-pwned-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

result = await agent.run("List recent Have I Been Pwned 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 Have I Been Pwned. 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 Have I Been Pwned 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 Have I Been Pwned MCP in Pydantic AI

Yes. Since Pydantic AI validates every tool response, the server output is parsed into your models automatically. If the data doesn't match, the agent throws a clear validation error.

Instantiate the MCPToolset with the server's HTTP URL. Pass it into your agent's toolsets list to make the functions available.

The framework expects a response. You should wrap your tool calls in a helper function that handles retries if the MCP server returns a 429 error.

The main benefit is correctness. You get strongly typed data from the HIBP service, which eliminates the guesswork and silent failures common in other frameworks.

It processes email addresses and password hash prefixes. All security is handled via TLS, and the server does not store your account identifiers.

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