How to Use the HireVue MCP in Pydantic AI

Use Pydantic AI with HireVue for type-safe recruitment automation.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect HireVue MCP to Pydantic AI

Create your Vinkius account to connect HireVue 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 HireVue with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe candidate management in Pydantic AI

Your agent requires validated data for every operation. It uses `create_candidate` and `update_candidate` with strict Pydantic model enforcement. If the HireVue API returns malformed data, your agent stops immediately. This prevents bad data from corrupting your recruiting database.

HireVue MCP Server interview control

Your agent schedules interviews with total precision. It calls `create_interview` and validates the response against your expected schema. If the tool output deviates from the spec, the agent throws a validation error. You never have to worry about silent failures during the booking process.

Accurate position tracking for Pydantic AI

The agent monitors your open roles by calling `list_positions`. It parses the response into your defined models, ensuring you always work with current job data. It then uses `get_position` to verify specific criteria before suggesting a candidate. This keeps your hiring funnel strictly aligned with your job requirements.

Setup guide

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

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

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

The framework automatically wraps MCP tool outputs in Pydantic models. If the server returns data that doesn't match your schema, the agent will fail loudly, allowing you to catch errors early.

Yes. Because every tool call is validated at runtime, you avoid the risk of hallucinated fields or unexpected data types affecting your recruitment records.

Install the necessary dependencies and initialize an MCPToolset pointing to your Vinkius host. Add this toolset to your agent's list, and you are ready to start calling tools.

You should implement retry logic within your agent's tool-calling loop. The framework gives you full control over how to handle errors returned by the HireVue API.

The server only processes candidate IDs and status updates during tool execution. Your resume files are kept separate, and the server strictly limits access to the metadata required for scheduling.

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