How to Use the Checkr MCP in Pydantic AI

Q: Can I use Pydantic AI to list all available screening packages from Checkr?

Yes, your agent calls the listscreeningpackages tool. Pydantic AI will return a list of validated objects, each representing a package, so you can reliably access their properties like name and ID in your code.

Q: What happens if the Checkr API changes when I'm using Pydantic AI?

Your agent will fail loudly with a ValidationError on the first call that gets the new, unexpected structure. This is a good thing—it alerts you to the change immediately instead of causing silent bugs down the line.

Build reliable, type-safe HR automations on Checkr 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 Checkr MCP to Pydantic AI

Create your Vinkius account to connect Checkr 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 Checkr with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Validated Checkr Objects

When your agent calls `get_candidate_details` or `get_report_details`, Pydantic AI automatically parses the JSON response into a Pydantic model. You get to work with a clean Python object, not a raw dictionary. If Checkr's API ever returns an unexpected structure or a field is missing, your code will raise a `ValidationError` immediately. This stops silent data corruption and makes your agent's logic far more predictable. You always know what data you're working with.

Build Correct-by-Construction Workflows

You can create a new candidate with `create_new_candidate`, get back a validated candidate object, and then pass its ID to `start_background_check`. Type safety flows through the entire process. This approach lets you build complex logic with confidence. Because you're using Pydantic AI, you can chain these calls together knowing the output of one tool is a valid, type-checked input for the next. It's a structured way to build agent actions that just work.

Use Any LLM with this MCP Server

Pydantic AI doesn't lock you into one LLM provider. You can use this Checkr MCP Server with models from OpenAI, Anthropic, Google, or even a local model you're running yourself. This gives you the flexibility to choose the right model for the job without rewriting your tool-using logic. The MCP Server for Checkr works the same way regardless of which LLM is driving your Pydantic AI agent.

Setup guide

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

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

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

Pydantic AI validates every API response from the Checkr MCP Server against a Pydantic model. If a field is missing or has the wrong data type, it raises an error instead of letting your agent use bad data.

Yes, your agent calls the `list_screening_packages` tool. Pydantic AI will return a list of validated objects, each representing a package, so you can reliably access their properties like name and ID in your code.

Your agent will fail loudly with a `ValidationError` on the first call that gets the new, unexpected structure. This is a good thing—it alerts you to the change immediately instead of causing silent bugs down the line.

Yes. Pydantic AI is model-agnostic. You can connect it to any LLM, including local ones you run yourself, and it will use the Checkr tools in the same type-safe way.

The server processes candidate information to interact with Checkr's API. Vinkius uses an ephemeral architecture, meaning the environment processing your request is torn down the instant it's complete. No candidate data is ever stored at rest on the MCP server.

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