How to Use the Lever MCP in Pydantic AI

Q: Can I use Pydantic AI to list Lever hiring stages?

You can call listhiringstages through the MCPToolset. The agent will receive the list and validate the response structure automatically.

Ensure type-safe recruitment automation by connecting Pydantic AI to your Lever ATS.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Lever MCP to Pydantic AI

Create your Vinkius account to connect Lever 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 Lever with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Type-safe opportunity updates in Pydantic AI

Every response from `update_opportunity_stage` is validated against your Pydantic models. If the ATS returns unexpected data, the agent stops before a mistake happens. You get reliable transitions for your candidates. It prevents the silent errors that usually plague ATS integrations.

Manage job postings with Pydantic AI

Use `create_job_posting` and `get_posting_details` with full runtime validation. Your agent ensures every field matches your required schema. This keeps your job data clean. You won't deal with corrupted records because the agent rejects anything that doesn't fit your models.

Validating candidate profiles

Your agent uses `get_candidate_profile` to pull data, and Pydantic AI checks the structure immediately. It guarantees that you have the right info for every applicant. You can trust the data flowing into your decision logic. It removes the risk of hallucinated fields or missing information.

Setup guide

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

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

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

Install the MCP-compatible Pydantic AI package and use the MCPToolset. Point it to your server URL and include it in your agent's toolsets list.

Yes, the framework validates all incoming data against your defined models. Any mismatch triggers an immediate validation error to keep your agent stable.

You can call `list_hiring_stages` through the MCPToolset. The agent will receive the list and validate the response structure automatically.

The server supports both Streamable HTTP and SSE transports. You can configure your Pydantic AI setup to use whichever your architecture requires.

Data flows directly from Lever to your agent through the MCP connection. Your Pydantic models define exactly what data is processed and stored.

Use it with your favorite AI tools

Connect this server to Cursor, Claude, VS Code, and more.

OpenAI Agents SDK sdk-python