How to Use the CATS ATS MCP in Pydantic AI

Q: How do I initialize the CATS ATS MCP Server in Pydantic AI?

Install pydantic-ai-slimmcp. Create an MCPToolset pointing to your Vinkius HTTP endpoint. Pass it to the toolsets array in your Agent setup.

Q: Why use Pydantic AI for CATS ATS over basic SDKs?

Correctness. If you need guaranteed data structures from getjobdetails, runtime validation prevents hallucinated fields from breaking your application.

Q: Can Pydantic AI handle the CATS ATS company lists?

Yes. When the agent calls listrecruitmentcompanies, the framework ensures the returned list matches your predefined schema before the LLM even sees it.

Type-safe CATS ATS integration for Pydantic AI. Validate every candidate profile and job order against strict Python models 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 CATS ATS MCP to Pydantic AI

Create your Vinkius account to connect CATS ATS 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 CATS ATS with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Catch bad ATS data with Pydantic AI

Recruitment databases are notorious for messy data. Missing emails, malformed phone numbers, and broken formatting ruin automated workflows. When your agent calls `get_candidate_details` through the MCP Server, this framework validates the JSON response against your exact Pydantic schemas. If the ATS returns a string where an integer should be, the system fails loudly. You get a clear validation error instead of silent corruption downstream. Your application only processes clean, verified applicant records.

Switch LLMs without rewriting MCP Server logic

You might start building with OpenAI, then realize Claude handles resume parsing better. Because the framework is model-agnostic, you swap the LLM without touching your tool configuration. The agent still knows exactly how to execute `list_job_orders`. The underlying connection relies on the unified toolset approach. Your agent runs `search_candidates` to find applicants, and the framework handles the translation between your chosen model and the ATS API.

Parse recruiter notes into typed objects

Free-text recruiter notes are useless for structured analysis. Your agent pulls raw logs using `list_recruitment_activities` and forces the LLM to extract specific fields like interview dates and sentiment scores. It then links these typed objects to the right hiring managers by calling `list_recruitment_contacts`. You transform a messy web of human input into a rigid, queryable database structure.

Setup guide

Set up CATS ATS 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": {
        "cats-ats-mcp": {
            "url": "https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
        }
    }
})

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

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

Install `pydantic-ai-slim[mcp]`. Create an `MCPToolset` pointing to your Vinkius HTTP endpoint. Pass it to the `toolsets` array in your Agent setup.

Correctness. If you need guaranteed data structures from `get_job_details`, runtime validation prevents hallucinated fields from breaking your application.

Yes. When the agent calls `list_recruitment_companies`, the framework ensures the returned list matches your predefined schema before the LLM even sees it.

Use the Streamable HTTP transport provided by Vinkius. The older `MCPServerHTTP` class is deprecated in newer versions of the framework.

The integration operates within an ephemeral V8 sandbox. When fetching sensitive items like home addresses or interview feedback, the system handles authentication securely and retains zero state after the request finishes.

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