How to Use the ArcGIS MCP in OpenAI Agents SDK

Build production-grade spatial logic into your OpenAI Agents SDK apps with direct access to ArcGIS mapping tools.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect ArcGIS MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Batch geocoding for OpenAI Agents SDK

Feed large arrays of addresses directly into your agent pipeline. The `batch_geocode_addresses` tool handles up to 1000 entries per request, letting you process bulk location data without custom batching logic. Your agent uses `find_address_candidates` to turn raw text strings into precise coordinates. This keeps your location data accurate before it hits your internal databases.

Route optimization with ArcGIS

Calculate complex travel paths using `solve_nav_route` and `solve_vehicle_routing`. Your agent parses your specific JSON order strings to determine turn-by-turn directions for your fleet. It handles the heavy lifting of spatial calculation while you keep your OpenAI Agents SDK logic focused on high-level decision making. You get the math done without writing a single line of GIS code.

Spatial analysis for your agent

Run `calculate_od_matrix` to generate travel time and distance grids for your logistics modeling. This MCP server lets your agent query real-world road network data instantly. Use `calculate_service_area` to define boundaries based on drive times or distances. It turns abstract location requests into actionable spatial polygons for your application.

Setup guide

Set up ArcGIS 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 ArcGIS tools at runtime.
3

Create your Agent

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

Run the agent

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

You initialize an MCPServerStreamableHttp instance with your endpoint URL. Pass this object into your Agent constructor's mcp_servers list to let the framework auto-discover the available tools.

Yes, you can use the built-in guardrails in the SDK to verify the spatial data before your agent acts on it. This prevents the agent from processing malformed coordinate arrays.

Absolutely. Setting cacheToolsList=True in your server definition improves performance by reducing the number of introspection calls made to the ArcGIS MCP server.

The server returns structured error responses if an address doesn't resolve. Your agent catches these failures and can trigger a retry or flag the record for human review.

Your spatial data is processed through an ephemeral V8 sandbox that clears after every request. The system only handles raw coordinate and address strings, ensuring no persistent storage of your inputs occurs.

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