How to Use the Join MCP in Pydantic AI

Q: Does this MCP Server support metadata lookups in Pydantic AI?

Yes. Your agent can query listdepartments, listlocations, and listusers to build fully validated organizational maps.

Get type-safe candidate tracking and job management with Pydantic AI and the Join 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 Join MCP to Pydantic AI

Create your Vinkius account to connect Join 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 Join with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate candidate profiles at runtime with Pydantic AI

Your agent calls `list_candidates` and validates every single email, phone number, and job association against strict Python schemas. If the API returns malformed candidate data, the system catches it instantly. It uses `get_candidate` to fetch detailed profiles for interview loops. Pydantic AI ensures that no fields are missing before the data reaches your recruiters.

Prevent schema drift in your MCP Server workflows

When fetching open roles with `list_jobs`, the framework guarantees the returned job titles and IDs match your expected data models. This prevents silent failures in your downstream hiring apps. The agent checks job details using `get_job` to confirm that descriptions and requirements are fully populated. This keeps your job board integrations running without errors.

Track application pipelines with absolute type safety

Run `list_applications` to monitor your incoming talent pipeline. The agent validates every application status and form answer before parsing them. It queries `get_application` to retrieve internal recruiter notes and interview feedback. The framework handles the JSON response, ensuring your agent never processes corrupted data.

Setup guide

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

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

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

Use the unified MCP toolset constructor with the HTTP server URL. Pass the toolset directly into your agent setup.

The framework raises a validation error immediately. This stops your agent from making decisions based on corrupted candidate profiles.

Yes. The toolset is completely model-agnostic, meaning you can run candidate screening with OpenAI, Anthropic, or local models.

Yes. Your agent can query `list_departments`, `list_locations`, and `list_users` to build fully validated organizational maps.

All candidate tracking data and application statuses are validated locally in your runtime environment. No external logs are created.

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

Mastra AI sdk-typescript

Start using the Join MCP today

We host it, we monitor it, we maintain it. You just paste one token.

Get started