How to Use the Gem MCP in Pydantic AI

Q: How do I get my Pydantic AI agent to use the Gem tools?

First, pip install "pydantic-ai-slimmcp". Then create an MCPToolset instance with your Vinkius server URL and pass it to your Agent's toolsets list. Pydantic AI handles the rest.

Q: How does error handling work for Gem tools in a Pydantic AI agent?

If a tool like getcandidatedetails gets a response from the server that doesn't match the expected Pydantic model, it throws a ValidationError. You can wrap your tool calls in a standard try/except block to handle these cases gracefully. It's predictable and Pythonic.

Add type-safe, validated access to your Gem MCP Server right inside your Pydantic AI agent.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Gem MCP to Pydantic AI

Create your Vinkius account to connect Gem 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 Gem with Pydantic AI

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Get Correct Candidate Data, Every Time

This MCP server gives your agent tools to interact with your Gem CRM. When your Pydantic AI agent calls `get_candidate_details`, the response is automatically parsed and validated against a Pydantic model. If Gem ever returns an unexpected field or data type, your code will raise a `ValidationError` immediately. No more silent data corruption. You can trust that the data you're working with is exactly what you expect. This is critical when you're making decisions based on candidate info from `list_candidates` or checking their history with `list_candidate_notes`.

Build Reliable Recruiting Automation

Use your agent to safely modify your talent pipeline. It can add a new person with `create_crm_candidate` or change their status with `update_crm_candidate`. Because Pydantic AI validates the *inputs* to these tools as well, you're less likely to send a bad request to the Gem API in the first place. This makes your automation robust. You can build a workflow that pulls project requirements with `get_project_details`, finds matching candidates, and updates their records, all with the confidence that every step is type-checked. Your agent won't quietly fail if an API response changes.

A Flexible Connector for Any LLM

Pydantic AI is model-agnostic, and so is this server. You can use OpenAI, Gemini, Anthropic, or even a local model to power your agent. The Gem tools, like `list_outreach_sequences` and `list_talent_projects`, will work exactly the same way. The connection is simple. You just point the `MCPToolset` at your Vinkius URL. There's no complex setup, so you can focus on building your agent's logic, not on writing boilerplate API client code.

Setup guide

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

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

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

First, `pip install "pydantic-ai-slim[mcp]"`. Then create an `MCPToolset` instance with your Vinkius server URL and pass it to your `Agent`'s `toolsets` list. Pydantic AI handles the rest.

Data integrity. Pydantic AI validates every single API call to and from the Gem MCP Server. If the `list_crm_custom_fields` tool returns data in a format you don't expect, your agent will raise an error instead of guessing or failing silently.

Yes. Pydantic AI lets you plug in any LLM, including models running locally via Ollama or llama.cpp. Your agent can use local intelligence to decide when to call Gem tools like `add_candidate_note`, keeping sensitive data flow under your control.

If a tool like `get_candidate_details` gets a response from the server that doesn't match the expected Pydantic model, it throws a `ValidationError`. You can wrap your tool calls in a standard try/except block to handle these cases gracefully. It's predictable and Pythonic.

The server processes candidate recruiting data, like contact info from `create_crm_candidate` or interview feedback from `add_candidate_note`. Vinkius ensures data is handled in a sandboxed environment for each request. The connection is encrypted, and no candidate information is ever written to disk on our end.

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