How to Use the Google Maps Platform MCP in OpenAI Agents SDK

Q: What happens if my agent passes a bad address to the geocoding tools?

The geocodeaddress tool returns a structured error payload which the agent reads and uses to self-correct. It will typically ask the user for clarification or try to resolve the name using findplacefromtext first.

Give your OpenAI Agents SDK assistants real-time routing, geocoding, and distance calculations with built-in execution guardrails.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Google Maps Platform MCP to OpenAI Agents SDK

Create your Vinkius account to connect Google Maps Platform 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 Maps Platform with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Guardrail-Backed Routing in OpenAI Agents SDK

Your OpenAI Agents SDK agents use `get_directions` and `get_distance_matrix` to calculate exact travel times and turn-by-turn routes directly inside their execution loops. By exposing these tools to your agent stream, the model handles complex logistics coordination without hitting custom routing engines. The OpenAI tracing dashboard logs every single step, ensuring you see exactly how the agent parses coordinate strings. Because the SDK enforces strict runtime schemas, your agent won't pass malformed pipe-separated coordinates when invoking these heavy mapping endpoints.

Precise Address Geocoding for OpenAI Agents SDK

Raw text strings are a nightmare for spatial databases, but this MCP server lets your agent clean them up instantly using `geocode_address` and `reverse_geocode`. The agent turns messy, user-submitted location descriptions into clean latitude and longitude coordinates. If the input is too vague, the agent triggers `find_place_from_text` to verify the location before committing to a database write. The OpenAI Agents SDK manages these multi-step validation loops natively, preventing your backend from storing junk coordinates.

Enrich Agent Context with Local Place Details

Give your agents the ability to analyze physical surroundings by searching for nearby businesses using `search_nearby_places`. Your agent retrieves a list of filtered establishments within a precise meter radius. From there, the agent invokes `get_place_details` to pull operating hours, reviews, and contact info, feeding this structured data directly into your custom agent handoff workflows using this MCP server. You get clean, verified local business intelligence without writing custom API wrapper logic.

Setup guide

Set up Google Maps Platform 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 Maps Platform tools at runtime.
3

Create your Agent

Pass the MCP to Agent(mcp_servers=[server]). The agent receives Google Maps Platform 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 Maps Platform 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 Maps Platform Agent",
            instructions="You have access to Google Maps Platform 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 Maps Platform. 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 Maps Platform 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 Maps Platform MCP in OpenAI Agents SDK

You install the SDK via pip and use the MCPServerStreamableHttp client pointing to your Vinkius endpoint. Pass this server instance inside the mcp_servers list when initializing your Agent constructor to let the model auto-discover all nine mapping tools.

Yes, your agent can pass multiple pipe-separated coordinates to the get_distance_matrix tool to calculate complex logistics grids. The SDK's built-in tracing keeps a clear record of these high-volume API calls so you can monitor usage and latency.

The SDK lets you define execution guardrails that inspect tool calls before they run, letting you block expensive operations like repeated get_place_details calls. You can also set cacheToolsList to true to avoid redundant schema discovery roundtrips.

The geocode_address tool returns a structured error payload which the agent reads and uses to self-correct. It will typically ask the user for clarification or try to resolve the name using find_place_from_text first.

Your physical addresses and GPS coordinates are processed inside Vinkius's isolated V8 sandboxes before hitting Google's endpoints. No location data is cached or stored on the hosting infrastructure, ensuring strict transit-only privacy compliance for your spatial queries.

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