How to Use the InfoVetted MCP in Pydantic AI

Q: Can my pydantic-ai agent cancel InfoVetted background checks?

Yes, your agent can call cancelactivevetting to stop an ongoing check. The response is validated to ensure the cancellation was successfully registered by the API before the agent proceeds.

Q: What happens if InfoVetted returns a new check type?

When your agent calls listsupportedchecktypes, the framework validates the list. If a new check type is introduced, your Pydantic models will catch it, allowing you to update your application logic to support the new screening option.

Run type-safe candidate background checks with Pydantic AI, validating every screening response at runtime.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect InfoVetted MCP to Pydantic AI

Create your Vinkius account to connect InfoVetted 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 InfoVetted with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Enforce strict type safety on candidate screenings

The `get_contact_details` tool retrieves candidate information and validates the returned JSON against strict Python schemas at runtime. If the API response contains unexpected fields or missing data, the system raises a validation error immediately. This strict validation prevents your agent from acting on corrupt or incomplete candidate profiles. You don't have to worry about the agent hallucinating screening results. Every field in the response from `get_vetting_request_status` must match your Pydantic models exactly before the data is processed.

Safe screening execution with this MCP Server

The `create_new_vetting_check` tool gives your type-safe agent the ability to initiate screenings with guaranteed data structures. Your agent can call `create_new_vetting_check` and `create_screening_contact` without risking runtime type errors. Pydantic validates that candidate names, emails, and check types are formatted correctly before the API is ever hit. If a database field is malformed, the validation layer catches it before calling `create_contact_group`. This keeps your external candidate groups clean and prevents API errors from halting your hiring pipeline.

Verify connectivity and manage webhooks safely

The `check_api_connectivity` tool verifies the connection status before starting a batch of background checks. Your agent can run this check to ensure the external service is online. Failing gracefully becomes simple when you can intercept network issues before they touch candidate records. You can also audit your notification setup by calling `list_configured_webhooks`. The agent parses the active webhooks into typed models, making it easy to confirm that your background check results are being sent to the correct endpoints.

Setup guide

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

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

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

The framework wraps the MCP tools and validates every JSON payload against runtime schemas. If a tool like `get_contact_details` returns unexpected data, the framework raises a validation error, preventing corrupt data from entering your database.

Use the unified toolset class to connect to your Vinkius HTTP endpoint. Pass this MCP Server directly to your Agent constructor, and the model-agnostic agent will automatically discover tools like `create_screening_contact`.

Yes, your agent can call `cancel_active_vetting` to stop an ongoing check. The response is validated to ensure the cancellation was successfully registered by the API before the agent proceeds.

When your agent calls `list_supported_check_types`, the framework validates the list. If a new check type is introduced, your Pydantic models will catch it, allowing you to update your application logic to support the new screening option.

All candidate background check data, including education verification and criminal history records, is processed inside secure, ephemeral V8 isolates. The MCP connection between Pydantic AI and the Vinkius endpoint is fully encrypted, and no sensitive personal data is stored on our servers.

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