How to Use the UpGuard MCP in Pydantic AI

Q: Can I rely on UpGuard for vendor risk data using Pydantic AI?

Yes. When you use getvendor or listvendorrisks, the resulting data is validated against a schema, meaning you get predictable and reliable security metrics every time.

Q: What type of network asset tracking does UpGuard offer with Pydantic AI?

The tools listmonitoreddomains and listmonitoredips provide structured lists. Your agent knows exactly how to parse the results, eliminating guesswork about IP or domain formats.

Q: Is UpGuard reliable for identity breach tracking when using Pydantic AI?

The listidentitybreaches tool delivers data that is strictly validated. This means your agent can trust the structure of the compromised identities without worrying about corrupted fields.

Get guaranteed, validated security data with Pydantic AI's 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 UpGuard MCP to Pydantic AI

Create your Vinkius account to connect UpGuard 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 UpGuard with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate Account and User Risk Data

When your agent runs `list_account_risks`, you get a structured output that guarantees all fields are present and correctly formatted. This prevents the kind of silent corruption that messes up complex analysis. Similarly, when calling `list_user_risks` to check user profiles, Pydantic ensures the resulting data structure matches your expectations every time.

Structure Third-Party Security Assessment

Checking vendor security is where type safety shines. Calling `get_vendor` gives you a guaranteed schema for that vendor's details. If the API messes up, your agent fails loudly—you know it immediately. This same guarantee holds true when listing partners with `list_vendors`, ensuring every entry has the expected data fields.

Confirm Asset and Breach Data Integrity

You can run `list_monitored_domains` and `list_monitored_ips` knowing that the resulting list will always conform to a strict structure. There are no unexpected data types popping up in your workflow. For identity tracking, calling `list_identity_breaches` guarantees the breach records follow the expected format, making downstream processing reliable.

Setup guide

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

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

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

The MCP Server forces every response into a known Python type. If any tool call, like `list_account_risks`, returns unexpected JSON, your agent fails immediately with an explicit validation error.

Yes. When you use `get_vendor` or `list_vendor_risks`, the resulting data is validated against a schema, meaning you get predictable and reliable security metrics every time.

The tools `list_monitored_domains` and `list_monitored_ips` provide structured lists. Your agent knows exactly how to parse the results, eliminating guesswork about IP or domain formats.

The `list_identity_breaches` tool delivers data that is strictly validated. This means your agent can trust the structure of the compromised identities without worrying about corrupted fields.

This server touches identity breach records and user risk profiles. It guarantees that the structured output from `list_identity_breaches` and `list_user_risks` is always correct.

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