How to Use the Greenhouse MCP in Pydantic AI

Q: How do I register Greenhouse tools in Pydantic AI?

Initialize MCPToolset with your Vinkius streamable HTTP URL. Pass this object into the toolsets argument of your Agent constructor to expose all 12 recruiting tools.

Q: Does Pydantic AI validate Greenhouse candidate schemas?

Yes, the framework validates all incoming data from getcandidate and outgoing payloads for createcandidate. It guarantees that your Python code only processes data matching your exact type definitions.

Q: Can I use Pydantic AI with Greenhouse over SSE using this MCP Server?

Yes, the MCPToolset class supports both streamable HTTP and SSE transports. This allows your agent to maintain a persistent connection to the Greenhouse API via Vinkius.

Build zero-hallucination recruiting workflows with Pydantic AI and our Greenhouse MCP Server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Greenhouse MCP to Pydantic AI

Create your Vinkius account to connect Greenhouse 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 Greenhouse with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate candidate creation payloads with Pydantic AI

The `create_candidate` tool requires structured payloads to prevent database corruption. Pydantic AI validates every single field against your defined schemas at runtime, stopping malformed resumes before they hit Greenhouse. If your agent tries to pass a string where an integer is expected, the framework raises a validation error. This keeps your candidate database clean and ensures your automation is completely reliable.

Enforce strict data models on Greenhouse MCP Server jobs

The `list_jobs` tool outputs active job configurations that your agent must parse accurately. Pydantic AI maps this API response to strict Python classes, ensuring fields like department IDs are perfectly typed. Your agent calls `get_job` and `list_job_stages` to verify that every open role has the correct interview milestones. Any missing stages trigger immediate validation failures, alerting your team to incomplete setups.

Map company structure without silent data corruption

The `list_users` tool returns your team directory, which must align with physical locations. Pydantic AI processes this alongside `list_offices` and `list_departments` to verify that managers are assigned to valid locations. By enforcing strict types on office and department records, you prevent routing errors. The agent cannot assign a candidate to a non-existent department because the framework catches the discrepancy instantly.

Setup guide

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

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

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

Initialize `MCPToolset` with your Vinkius streamable HTTP URL. Pass this object into the `toolsets` argument of your `Agent` constructor to expose all 12 recruiting tools.

Yes, the framework validates all incoming data from `get_candidate` and outgoing payloads for `create_candidate`. It guarantees that your Python code only processes data matching your exact type definitions.

Yes, the `MCPToolset` class supports both streamable HTTP and SSE transports. This allows your agent to maintain a persistent connection to the Greenhouse API via Vinkius.

Pydantic AI will fail immediately with a validation error rather than letting your agent make decisions based on incomplete data. This prevents downstream automation errors in your recruiting pipeline.

All data validation occurs locally within your Python runtime. This MCP Server runs on Vinkius's secure, isolated infrastructure, ensuring candidate profiles, application status history, and job parameters are never logged or exposed to external networks.

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