How to Use the ApplicantStack MCP in Pydantic AI

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

Install the pydantic-ai-slimmcp package and use the MCPToolset class. Pass your Vinkius HTTP URL to the toolset and reference it in your Pydantic AI agent's toolsets parameter.

Build type-safe hiring workflows using Pydantic AI and ApplicantStack.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ApplicantStack MCP to Pydantic AI

Create your Vinkius account to connect ApplicantStack 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 ApplicantStack with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe resume parsing with Pydantic AI

The `list_candidates` tool feeds candidate data into your Pydantic AI agent via our MCP Server, where every field is validated against strict Python types. If an ApplicantStack record contains malformed data, the framework catches it before your model processes it. Using `get_candidate` ensures you get structured profiles that fit your exact schema definitions. This prevents silent failures when your Pydantic AI agent parses complex resume histories.

Validate job listings before agent matching

The `list_jobs` tool retrieves your active openings, which Pydantic AI validates against your internal job models. You ensure that every ApplicantStack job has a valid title, department, and description before passing them to the LLM. The `get_job` tool pulls detailed requirements for a single opening, allowing your Pydantic AI agent to run precise candidate matching. This guarantees your matching logic operates on clean, validated data.

Safe pipeline transitions in ApplicantStack

The `update_candidate` tool changes candidate stages, backed by Pydantic AI runtime validation to ensure stage names are correct. This prevents your agent from sending invalid status updates to your ATS. To keep your agent running smoothly, the `get_account_check` tool verifies your ApplicantStack connection before starting any complex multi-step workflows. If the connection drops, your Pydantic AI application handles the error gracefully.

Setup guide

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

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

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

Install the pydantic-ai-slim[mcp] package and use the MCPToolset class. Pass your Vinkius HTTP URL to the toolset and reference it in your Pydantic AI agent's toolsets parameter.

Pydantic AI will raise a validation error at runtime instead of letting your agent hallucinate missing data. This guarantees that your candidate and job data matches your schema exactly.

Yes, Pydantic AI is model-agnostic. You can run local models or commercial APIs while using the same ApplicantStack tools to fetch candidate lists.

Yes, the MCPToolset supports both SSE and Streamable HTTP transports. This allows you to connect your Pydantic AI agent to Vinkius using your preferred communication protocol.

Pydantic AI runs validation locally in your environment, while the Vinkius MCP Server acts as an ephemeral proxy. Your candidate profiles, salaries, and background checks are never stored or exposed to external third parties.

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