How do I get an API Key for Gem?

Team Admins can generate API keys in the Team Settings dashboard of the Gem web application.

Can I search for candidates across all projects?

Yes, the 'list_candidates' tool retrieves a global list of candidates, which you can then narrow down using IDs or details.

Is it possible to log interview notes via the agent?

Yes! Use the 'add_candidate_note' tool and provide the Candidate ID and your text to instantly update their record in the CRM.

How do I see which sequences a candidate is in?

The 'get_candidate_details' tool retrieves the full metadata payload, which includes information about outreach and automated messaging state.

Gem MCP Server for Pydantic AI 12 tools — connect in under 2 minutes

Name: Gem
Availability: InStock
Author: Vinkius

ai.pydantic.dev/mcp

Built by Vinkius GDPR 12 Tools SDK

Pydantic AI brings type-safe agent development to Python with first-class MCP support. Connect Gem through Vinkius and every tool is automatically validated against Pydantic schemas. catch errors at build time, not in production.

Get MCP Server for AI Agents

ASK AI ABOUT THIS MCP SERVER

Open in ChatGPT Open in Claude Open in Perplexity

Vinkius supports streamable HTTP and SSE.

python

import asyncio
from pydantic_ai import Agent
from pydantic_ai.mcp import MCPServerHTTP

async def main():
    # Your Vinkius token. get it at cloud.vinkius.com
    server = MCPServerHTTP(url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp")

    agent = Agent(
        model="openai:gpt-4o",
        mcp_servers=[server],
        system_prompt=(
            "You are an assistant with access to Gem "
            "(12 tools)."
        ),
    )

    result = await agent.run(
        "What tools are available in Gem?"
    )
    print(result.data)

asyncio.run(main())

Fully ManagedVinkius Servers

60%Token savings

High SecurityEnterprise-grade

IAMAccess control

EU AI ActCompliant

DLPData protection

V8 IsolateSandboxed

Ed25519Audit chain

<40msKill switch

Stream every event to Splunk, Datadog, or your own webhook in real-time

* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure

About Gem MCP Server

Connect your Gem recruitment CRM to any AI agent to automate your talent sourcing and candidate relationship management through the Model Context Protocol (MCP). Gem is the AI-first recruiting platform that helps modern teams find, engage, and hire top talent. This MCP server enables you to manage your candidate database, organize talent projects, and retrieve detailed interaction histories directly through natural conversation.

Pydantic AI validates every Gem tool response against typed schemas, catching data inconsistencies at build time. Connect 12 tools through Vinkius and switch between OpenAI, Anthropic, or Gemini without changing your integration code. full type safety, structured output guarantees, and dependency injection for testable agents.

Key Features

Candidate Oversight — List all candidates in your CRM, retrieve detailed profiles, and create new records instantly to maintain a full talent pipeline.
Talent Project Management — Access your sourcing projects and fetch detailed metadata to track how your talent pools are growing.
Interaction Logging — Access historical notes and interaction logs for candidates, or programmatically log new notes from your chat interface.
Outreach Insights — List active outreach sequences and automated messaging campaigns to understand your engagement status.
Custom Metadata — Retrieve the definitions of custom fields configured for your team to maintain consistent data tracking.
Workforce Collaboration — List all team members and recruiters in the account to verify ownership and assignments.
Real-time Synchronization — Keep your recruiting data accessible to your AI assistant without leaving your primary workspace.

The Gem MCP Server exposes 12 tools through the Vinkius. Connect it to Pydantic AI in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.

How to Connect Gem to Pydantic AI via MCP

Follow these steps to integrate the Gem MCP Server with Pydantic AI.

Install Pydantic AI

Run pip install pydantic-ai

Replace the token

Replace [YOUR_TOKEN_HERE] with your Vinkius token

Run the agent

Save to agent.py and run: python agent.py

Explore tools

The agent discovers 12 tools from Gem with type-safe schemas

Why Use Pydantic AI with the Gem MCP Server

Pydantic AI provides unique advantages when paired with Gem through the Model Context Protocol.

Full type safety: every MCP tool response is validated against Pydantic models, catching data inconsistencies before they reach your application

Model-agnostic architecture. switch between OpenAI, Anthropic, or Gemini without changing your Gem integration code

Structured output guarantee: Pydantic AI ensures tool results conform to defined schemas, eliminating runtime type errors

Dependency injection system cleanly separates your Gem connection logic from agent behavior for testable, maintainable code

Gem + Pydantic AI Use Cases

Practical scenarios where Pydantic AI combined with the Gem MCP Server delivers measurable value.

Type-safe data pipelines: query Gem with guaranteed response schemas, feeding validated data into downstream processing

API orchestration: chain multiple Gem tool calls with Pydantic validation at each step to ensure data integrity end-to-end

Production monitoring: build validated alert agents that query Gem and output structured, schema-compliant notifications

Testing and QA: use Pydantic AI's dependency injection to mock Gem responses and write comprehensive agent tests

Gem MCP Tools for Pydantic AI (12)

These 12 tools become available when you connect Gem to Pydantic AI via MCP:

add_candidate_note

Log an interaction

create_crm_candidate

Add new candidate

get_candidate_details

Get candidate metadata

get_project_details

Get project metadata

list_candidate_notes

List interactions

list_candidates

List CRM candidates

list_crm_custom_fields

List team fields

list_outreach_sequences

List sequences

list_recruiting_team

List Gem users

list_talent_projects

List Gem projects

update_crm_candidate

Modify candidate

verify_api_connection

Check connection

Example Prompts for Gem in Pydantic AI

Ready-to-use prompts you can give your Pydantic AI agent to start working with Gem immediately.

"List all active candidates in my Gem CRM."

"Show me the interactions history for candidate '12345'."

"Create a new candidate record for 'Alice Smith' (alice@email.com)."

Troubleshooting Gem MCP Server with Pydantic AI

Common issues when connecting Gem to Pydantic AI through the Vinkius, and how to resolve them.

MCPServerHTTP not found

Update: pip install --upgrade pydantic-ai

Gem + Pydantic AI FAQ

Common questions about integrating Gem MCP Server with Pydantic AI.

How does Pydantic AI discover MCP tools?

Create an MCPServerHTTP instance with the server URL. Pydantic AI connects, discovers all tools, and generates typed Python interfaces automatically.

Does Pydantic AI validate MCP tool responses?

Yes. When you define result types as Pydantic models, every tool response is validated against the schema. Invalid data raises a clear error instead of silently corrupting your pipeline.

Can I switch LLM providers without changing MCP code?

Absolutely. Pydantic AI abstracts the model layer. your Gem MCP integration works identically with OpenAI, Anthropic, Google, or any supported provider.