How to Use the Geocode.xyz MCP in OpenAI Agents SDK

Q: How do I connect Geocode.xyz to the OpenAI Agents SDK?

Install the framework with pip install openai-agents. Create an MCPServerStreamableHttp instance pointing to the Vinkius endpoint. Pass it to your agent constructor via the mcpservers array inside an async context manager.

Q: Can my OpenAI Agents SDK system read user IP addresses with Geocode.xyz?

Yes. The ipgeolocation tool maps an IP address to a physical region. Your agent can use this to localize responses before asking the user for their exact location.

Q: How does caching improve this MCP Server's performance?

Tool discovery takes time. By setting cacheToolsList=True, the SDK remembers the available tools across turns. This drops latency significantly for conversational agents.

Give your OpenAI Agents SDK production-ready location parsing and geocoding.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Geocode.xyz MCP to OpenAI Agents SDK

Create your Vinkius account to connect Geocode.xyz 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 Geocode.xyz with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Extract Locations from Text with Geocode.xyz

The `geoparse` tool identifies and extracts location names from free-form text. Your agents read emails, chat logs, and support tickets constantly. Instead of writing regex to find city names, you pass the raw string to this tool. It uses POST requests under the hood to handle massive text blocks without hitting URL length limits. OpenAI's guardrails validate the action before execution. If the agent tries to send poorly formatted data, the framework catches it. You see the exact extraction steps in your OpenAI tracing dashboard, making debugging fast and deterministic.

Convert Addresses to Coordinates

The `forward_geocode` tool converts a place name or address into geographic coordinates. Production routing systems require exact latitude and longitude, not messy user input. You feed the tool a place name, and it returns the precise coordinates your downstream APIs demand. Agents can hand off these coordinates to specialized delivery or mapping sub-agents. Because this MCP Server runs on a standardized protocol, you avoid writing custom integration code. The agent discovers the capability dynamically and calls it when the prompt requires spatial awareness.

MCP Server Address Autocomplete

The `autocomplete` tool provides suggestions for partial street names, postal codes, or city names. Users type fast and make mistakes. When your agent asks a user for their address, it can run their partial input through this tool to get valid options. You want responses fast. Setting `cacheToolsList=True` in your setup ensures the agent does not waste time re-discovering this tool on every turn. The agent presents the corrected address options to the user, ensuring bad data never enters your database.

Setup guide

Set up Geocode.xyz 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 Geocode.xyz tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the framework with `pip install openai-agents`. Create an `MCPServerStreamableHttp` instance pointing to the Vinkius endpoint. Pass it to your agent constructor via the `mcp_servers` array inside an async context manager.

Yes. The `ip_geolocation` tool maps an IP address to a physical region. Your agent can use this to localize responses before asking the user for their exact location.

The SDK's built-in guardrails intercept the error. Your agent receives a clear failure state rather than crashing. It can then decide to retry the request or ask the user for clarification.

Tool discovery takes time. By setting `cacheToolsList=True`, the SDK remembers the available tools across turns. This drops latency significantly for conversational agents.

Your unstructured text passes through a strict V8 Isolate Sandbox. Vinkius executes the request ephemerally. The system discards the text immediately after returning the extracted locations, leaving no persistent records.

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