How to Use the Gem MCP in OpenAI Agents SDK

Q: How do I use the Gem tools with my OpenAI Agents SDK?

You pass the Vinkius URL to MCPServerStreamableHttp. The OpenAI agent automatically discovers the Gem tools like createcrmcandidate. Set cacheToolsList=True so it doesn't have to fetch the tool list on every run.

Q: Can an OpenAI agent add a candidate to a specific project in Gem?

Yes. Your agent would first use createcrmcandidate, then updatecrmcandidate to assign the new candidate ID to a project ID. It can find the right project ID by calling listtalentprojects first.

Build production-ready recruiting agents with OpenAI Agents SDK that manage your Gem pipeline, safely.

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 OpenAI Agents SDK

Create your Vinkius account to connect Gem to OpenAI Agents SDK 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 OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Manage Candidate Pipelines

Your agent can create and update candidate profiles in Gem. It uses `create_crm_candidate` to add a new person to your talent pool, then follows up with `update_crm_candidate` to move them between stages or projects. The OpenAI SDK's built-in guardrails can prompt for human approval before your agent modifies a high-value candidate's record. This isn't just about adding data. You can build specialized agents that hand off tasks—one agent finds prospects, another uses `get_candidate_details` to check for missing info, and a third logs interview feedback with `add_candidate_note`. You'll see every step in the OpenAI dashboard, so you know exactly what your agents did.

Track Outreach and Projects

Give your agent the ability to see your team's entire recruiting operation. It can pull a full list of your active jobs with `list_talent_projects` or check the status of an email campaign using `list_outreach_sequences`. This lets you build agents that can answer questions like, "How many candidates are in the sequence for the Senior Backend role?" You can also get a clear picture of your team's workload. The agent can call `list_recruiting_team` to see who's on the project, then cross-reference that with `list_candidates` assigned to them. This is perfect for building automated reporting agents that run daily and post updates to Slack.

Automate Recruiting with this MCP Server

This Gem MCP Server connects your recruiting data directly to your agent. Your agent can pull custom fields with `list_crm_custom_fields` to understand how your team segments talent, like "Willing to Relocate" or "Security Clearance Level." This context is critical for making smart decisions. Before running any complex workflows, your agent can ping `verify_api_connection` to make sure it has a live link to Gem. It's a simple check that prevents errors in long-running tasks, which is exactly what you need for a production system built with the OpenAI Agents SDK.

Setup guide

Set up Gem MCP in OpenAI Agents SDK

Prerequisites

Python 3.10+ installed
openai-agents package (pip install openai-agents)
Active Vinkius subscription with a valid endpoint token

1

Install the SDK

Run pip install openai-agents to install the OpenAI Agents SDK. The MCP integration is built-in — no extra dependencies needed.
2

Connect via SSE transport

Use MCPServerSse with your Vinkius endpoint URL. Replace [YOUR_TOKEN_HERE] with your token from cloud.vinkius.com. The SDK auto-discovers all Gem tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Gem tools as native definitions — JSON schemas resolve automatically.
4

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Gem tools and returns structured results. Copy the full example on the right to get started.

agent.py

import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerSse

async def main():
    async with MCPServerSse(
        url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
    ) as server:
        agent = Agent(
            name="Gem Agent",
            instructions="You have access to Gem tools.",
            mcp_servers=[server],
        )
        result = await Runner.run(agent, "List recent transactions")
        print(result.final_output)

asyncio.run(main())

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 OpenAI Agents SDK

You pass the Vinkius URL to `MCPServerStreamableHttp`. The OpenAI agent automatically discovers the Gem tools like `create_crm_candidate`. Set `cacheToolsList=True` so it doesn't have to fetch the tool list on every run.

Yes. Your agent would first use `create_crm_candidate`, then `update_crm_candidate` to assign the new candidate ID to a project ID. It can find the right project ID by calling `list_talent_projects` first.

Vinkius manages the MCP Server, so we handle API changes on our end. Your agent's tool definitions for Gem will update automatically the next time it connects, as long as `cacheToolsList` isn't set to an unreasonable duration.

The OpenAI Agents SDK doesn't have a simple tool name filter. Instead, you define access through the agent's instructions and guardrails. You can configure prompts that require human-in-the-loop approval before it runs sensitive tools like `update_crm_candidate`.

This server processes candidate PII, including names, emails, and notes from `list_candidate_notes`. Vinkius isolates each request in an ephemeral, zero-trust sandbox. Your OpenAI agent's connection is secured, and we never store your candidate data after the operation completes.

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