How to Use the JobScore MCP in Pydantic AI

Q: Can I use JobScore tools to build a typed state machine in Pydantic AI?

You can. By chaining tool calls like listjobs and getjob, you create a deterministic flow that the agent follows to manage your hiring data.

Get type-safe hiring data in Pydantic AI by connecting this MCP Server to your agent pipeline.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect JobScore MCP to Pydantic AI

Create your Vinkius account to connect JobScore 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 JobScore with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe candidate lookups

Every response from `get_candidate` is validated against your Pydantic schemas. If the API returns a malformed record, the agent stops immediately instead of propagating bad data. This prevents silent failures in your hiring workflows. You define the shape of your candidate profile, and the framework ensures the data matches your expectations every single time.

Strict job requirement validation

The agent calls `get_job` to pull role details and validates them against your internal models. This ensures the agent only works with jobs that have all required fields present. It handles the `list_jobs` output by mapping it to a collection of typed objects. This makes it impossible for the agent to hallucinate job IDs that don't exist in your account.

Robust MCP Server communication

The connection between your agent and the server is typed and predictable. Using the `MCPToolset`, you gain full visibility into the request-response cycle for every tool call. You can rely on the server to provide consistent data structures. Because the framework enforces strict types, your agent logic remains clean and free from manual parsing errors.

Setup guide

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

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

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

The framework automatically checks the server's output against your defined Pydantic models. Any field mismatch triggers a validation error before the agent processes the data.

Yes. The tools act as standard functions that return data structures. You wrap these in your Pydantic models to enforce strict schema adherence.

You can. By chaining tool calls like `list_jobs` and `get_job`, you create a deterministic flow that the agent follows to manage your hiring data.

The framework treats tool errors as exceptions. You catch these in your agent logic to provide graceful degradation or retry attempts.

It returns JSON objects containing candidate contact history, application stages, and resume highlights. These are then parsed into your predefined Pydantic classes.

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