How to Use the Google Contacts MCP in OpenAI Agents SDK

Q: How do I authenticate Google Contacts with the OpenAI Agents SDK?

You pass your Vinkius endpoint token directly into the MCPServerStreamableHttp parameter block. The platform handles the Google OAuth handshake behind the scenes, so your production agent never sees raw Google credentials.

Q: How does the OpenAI Agents SDK handle rate limits when calling Google Contacts?

The SDK uses the MCP connection with cacheToolsList=True to avoid redundant schema lookups on every turn. This optimization keeps your API footprint light and prevents your agent from hitting Google People API rate limits during bulk syncs.

Let your OpenAI Agents SDK production workflows manage, update, and query your Google Contacts directly through a secure gateway.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Contacts MCP to OpenAI Agents SDK

Create your Vinkius account to connect Google Contacts 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 Google Contacts with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Secure contact updates with OpenAI Agents SDK

`update_contact` requires an etag from `get_contact` to prevent overwriting concurrent updates during multi-agent handoffs. Your agent has to grab the current state first, check the version, and then push the write. If a conflict occurs, the OpenAI Agents SDK guardrails stop the execution chain before corrupting your address book. This keeps your production contacts clean when multiple specialized agents coordinate on a single account.

Smart directory searching and group filtering

`search_contacts` and `list_contact_groups` let your agent find specific subsets of your address book without pulling down thousands of records. This MCP Server exposes these endpoints directly to your runtime. Because the OpenAI Agents SDK handles agent handoffs, you can have one search agent locate the contact and hand the ID to a billing agent. This keeps token usage low and prevents the agent from getting lost in a massive contact list.

Managed contact lifecycle with the MCP Server

`delete_contact` and `create_contact` give your autonomous agent full control over your active network directory. The agent creates new entries from incoming emails and purges outdated ones based on your custom rules. You configure these destructive actions behind the SDK's built-in validation layer so no contact gets deleted without matching your exact criteria. Every single API call is recorded and traceable on your OpenAI dashboard.

Setup guide

Set up Google Contacts 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 Google Contacts tools at runtime.
3

Create your Agent

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

Run the agent

Call Runner.run(agent, prompt) to execute. The agent invokes the appropriate Google Contacts 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="Google Contacts Agent",
            instructions="You have access to Google Contacts 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 Google Contacts. 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 Google Contacts 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 Google Contacts MCP in OpenAI Agents SDK

You pass your Vinkius endpoint token directly into the `MCPServerStreamableHttp` parameter block. The platform handles the Google OAuth handshake behind the scenes, so your production agent never sees raw Google credentials.

Yes, you can filter the exposed tools during agent registration to exclude destructive actions. For example, you can omit `delete_contact` from the runtime tools list to ensure your agent only reads or updates entries.

The SDK uses the MCP connection with `cacheToolsList=True` to avoid redundant schema lookups on every turn. This optimization keeps your API footprint light and prevents your agent from hitting Google People API rate limits during bulk syncs.

The execution halts immediately and raises an error that your agent can catch and handle. Because `update_contact` uses etags, the SDK prevents the agent from writing stale data if another thread modified the contact first.

Your contact names, phone numbers, and email addresses run inside an ephemeral V8 sandbox that destroys itself after execution. Vinkius enforces a zero-trust architecture, meaning your address book data is never stored on disk or used for model training.

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