How to Use the Georef Argentina MCP in OpenAI Agents SDK

Clean up messy Argentine address data and resolve coordinates inside your production OpenAI Agents SDK pipelines with zero manual mapping.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Georef Argentina MCP to OpenAI Agents SDK

Create your Vinkius account to connect Georef Argentina 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 Georef Argentina with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Validate shipping addresses in OpenAI Agents SDK

Your agents can now parse messy, user-entered street names directly against official Argentine government databases. By calling `normalize_direccion`, your agent splits messy strings into structured street names, exact heights, and local administrative zones before executing high-value business logic. This avoids bad delivery data from hitting your database. By feeding the cleaned output directly into `get_vias`, your agent verifies that the street actually exists in the specified province without writing custom validation code.

Map exact administrative boundaries with this MCP Server

Stop guessing which municipality a neighborhood belongs to. Your agent uses `get_provincias`, `get_departamentos`, and `get_municipios` to dynamically build a clean, hierarchical representation of Argentine territory during conversational interactions. This MCP Server exposes these tools directly to your agent's reasoning loop. The agent identifies the correct administrative division on the fly, preventing routing errors and ensuring your database records match national standards.

Convert coordinates to official localities

When your agent receives raw latitude and longitude coordinates from a mobile app, it needs context. Using `reverse_geocoding`, the agent resolves those raw coordinates into official administrative areas instantly. Once resolved, your agent can call `get_localidades` to find nearby population centers. This gives your automated workflows the geographic context required to assign local drivers or calculate accurate tax jurisdictions.

Setup guide

Set up Georef Argentina 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 Georef Argentina tools at runtime.
3

Create your Agent

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

Run the agent

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

Your python code registers the Georef Argentina MCP server using `MCPServerStreamableHttp` within an async context manager. The SDK automatically queries the endpoint to discover tools like `normalize_direccion` and exposes them to your agent without manual JSON schema declarations.

Yes, you control tool access directly in the agent constructor. If you only want an agent to normalize addresses, pass only `normalize_direccion` in the tool configuration, preventing it from invoking `get_departamentos` or other administrative lookups.

Global mapping tools charge hefty API fees and often fail to match official government boundaries used for tax or legal purposes in Argentina. This MCP server queries the official government API directly, giving you authoritative data for administrative divisions like provinces and departments.

You can implement batching loops in your python agent scripts to handle multiple lookups sequentially. For heavy loads, caching the results of static lookups like `get_provincias` locally will keep your API usage within the upstream government limits.

No, this server acts as a zero-trust proxy. When your agent passes coordinates to `reverse_geocoding` or address strings to `normalize_direccion`, the data is sent straight to the official Argentine government API in an ephemeral sandbox and is never saved to disk.

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