How to Use the Geoapify MCP in OpenAI Agents SDK

Q: How does the OpenAI Agents SDK handle complex Geoapify tools like routeplanner?

The SDK lets your agent call routeplanner like any other tool. The key difference is the guardrails—you can require human approval before the agent executes the plan, ensuring the proposed route and cost make sense for your business.

Build production location agents with the OpenAI Agents SDK and get automatic guardrails for every Geoapify API call.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geoapify MCP to OpenAI Agents SDK

Create your Vinkius account to connect Geoapify 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 Geoapify with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Build Safe Dispatch Agents

Give your agent access to Geoapify's routing tools and let the OpenAI SDK's built-in guardrails keep it in check. Before your agent can burn through your budget with a massive `calculate_route_matrix` call, the SDK can enforce a confirmation step. This is how you build real dispatch systems that don't run wild. You can also design agent teams. A simple agent can handle user input with `geocode_autocomplete`, then hand off the validated address to a specialized logistics agent. That agent then uses `route_planner` to solve the routing problem. The entire handoff is visible and traceable in your OpenAI dashboard.

Interactive Geocoding with your OpenAI Agent

Turn location lookups into a conversation. Your agent can use `geocode_search` to find a location, then immediately follow up with `get_place_details` to pull its opening hours or phone number. The OpenAI Agents SDK makes this tool-chaining feel fluid and natural. This Geoapify MCP server exposes the tools, but the SDK gives you control. For instance, if an agent wants to act on a location derived from an IP address via `get_ip_info`, you can configure the agent to require human-in-the-loop approval. It's a simple way to add a layer of safety before taking action.

Analyze Geospatial Data at Scale

Some jobs are too big for a single API call. Let your agent use `create_batch_job` to queue up hundreds or thousands of geocoding or routing requests with Geoapify. The agent can then periodically check the status using `get_batch_job` without blocking its main thread. Once the batch job is done, the agent can process the results. It might use `calculate_isoline` to see which results fall within a 15-minute drive, or use `get_boundaries_consists_of` to group the locations by postal code. The whole workflow, from batch creation to final analysis, is one connected process.

Setup guide

Set up Geoapify 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 Geoapify tools at runtime.
3

Create your Agent

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

Run the agent

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

The SDK lets your agent call `route_planner` like any other tool. The key difference is the guardrails—you can require human approval before the agent executes the plan, ensuring the proposed route and cost make sense for your business.

Yes. While the MCP server exposes all 17 tools, you can configure your agent in the OpenAI SDK to only have access to a specific subset. This is useful for creating specialized agents that only perform one function, like geocoding addresses.

You get powerful Geoapify location tools combined with OpenAI's production-focused features like guardrails, agent-to-agent handoffs, and built-in observability. It's a setup designed for building reliable, real-world applications.

Just install the SDK, point it to the Vinkius MCP Server URL for Geoapify, and pass it to your Agent constructor. The tools are discovered automatically, so you can start prompting your agent with location-based tasks right away.

Your data, like addresses or coordinates sent to tools like `geocode_search`, is processed in an ephemeral sandbox on Vinkius. The environment for each request is isolated and destroyed after use, and it's all handled through a single, secure endpoint token.

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