ArcGIS MCP Server for OpenAI Agents SDK 10 tools — connect in under 2 minutes
The OpenAI Agents SDK enables production-grade agent workflows in Python. Connect ArcGIS through the Vinkius and your agents gain typed, auto-discovered tools with built-in guardrails — no manual schema definitions required.
ASK AI ABOUT THIS MCP SERVER
Vinkius supports streamable HTTP and SSE.
import asyncio
from agents import Agent, Runner
from agents.mcp import MCPServerStreamableHttp
async def main():
# Your Vinkius token — get it at cloud.vinkius.com
async with MCPServerStreamableHttp(
url="https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp"
) as mcp_server:
agent = Agent(
name="ArcGIS Assistant",
instructions=(
"You help users interact with ArcGIS. "
"You have access to 10 tools."
),
mcp_servers=[mcp_server],
)
result = await Runner.run(
agent, "List all available tools from ArcGIS"
)
print(result.final_output)
asyncio.run(main())
* Every MCP server runs on Vinkius-managed infrastructure inside AWS - a purpose-built runtime with per-request V8 isolates, Ed25519 signed audit chains, and sub-40ms cold starts optimized for native MCP execution. See our infrastructure
About ArcGIS MCP Server
Connect your ArcGIS account to any AI agent and take full control of your location and spatial intelligence through natural conversation.
The OpenAI Agents SDK auto-discovers all 10 tools from ArcGIS through native MCP integration. Build agents with built-in guardrails, tracing, and handoff patterns — chain multiple agents where one queries ArcGIS, another analyzes results, and a third generates reports, all orchestrated through the Vinkius.
What you can do
- Geocoding & Reverse Geocoding — Convert street addresses to coordinates instantly or discover the closest address to a specific longitude/latitude pair
- Batch Geocoding — Process bulk batches of up to 1000 geographical addresses in a single AI operation
- Route Solving — Calculate the optimal route between multiple stops, complete with turn-by-turn directions, travel time, and precise distances
- Vehicle Routing — Solve complex Vehicle Routing Problems (VRP) to optimize fleets and logistics deliveries
- Service Area Analysis — Calculate drive-time, walk-time, or travel-distance polygons reachable from a specific facility
- Origin-Destination Matrices — Compute travel constraints and cost matrices between multiple origins and tracking destinations
The ArcGIS MCP Server exposes 10 tools through the Vinkius. Connect it to OpenAI Agents SDK in under two minutes — no API keys to rotate, no infrastructure to provision, no vendor lock-in. Your configuration, your data, your control.
How to Connect ArcGIS to OpenAI Agents SDK via MCP
Follow these steps to integrate the ArcGIS MCP Server with OpenAI Agents SDK.
Install the SDK
Run pip install openai-agents in your Python environment
Replace the token
Replace [YOUR_TOKEN_HERE] with your Vinkius token from cloud.vinkius.com
Run the script
Save the code above and run it: python agent.py
Explore tools
The agent will automatically discover 10 tools from ArcGIS
Why Use OpenAI Agents SDK with the ArcGIS MCP Server
OpenAI Agents SDK provides unique advantages when paired with ArcGIS through the Model Context Protocol.
Native MCP integration via `MCPServerSse` — pass the URL and the SDK auto-discovers all tools with full type safety
Built-in guardrails, tracing, and handoff patterns let you build production-grade agents without reinventing safety infrastructure
Lightweight and composable: chain multiple agents and MCP servers in a single pipeline with minimal boilerplate
First-party OpenAI support ensures optimal compatibility with GPT models for tool calling and structured output
ArcGIS + OpenAI Agents SDK Use Cases
Practical scenarios where OpenAI Agents SDK combined with the ArcGIS MCP Server delivers measurable value.
Automated workflows: build agents that query ArcGIS, process the data, and trigger follow-up actions autonomously
Multi-agent orchestration: create specialist agents — one queries ArcGIS, another analyzes results, a third generates reports
Data enrichment pipelines: stream data through ArcGIS tools and transform it with OpenAI models in a single async loop
Customer support bots: agents query ArcGIS to resolve tickets, look up records, and update statuses without human intervention
ArcGIS MCP Tools for OpenAI Agents SDK (10)
These 10 tools become available when you connect ArcGIS to OpenAI Agents SDK via MCP:
batch_geocode_addresses
Addresses must be provided as an ArcGIS-compatible JSON array string. Geocode a bulk batch of up to 1000 addresses
calculate_od_matrix
Calculate travel time and distances between multiple origins and destinations
calculate_service_area
Facilities specified as lon,lat. Calculate drive-time, walk-time, or travel-distance service areas
find_address_candidates
Use this to turn text addresses into latitude and longitude. Find an address or place using ArcGIS Geocoding
find_address_country
g., USA, BRA, FRA). Ensures results are geographically bounded. Find an address filtered by a specific country
reverse_geocode
Coordinate format must be lon,lat (e.g. -117.19,34.05). Discover the closest address to a specific location (lon,lat)
solve_nav_route
Point sequence must be provided as lon,lat;lon,lat. Returns detailed turn-by-turn directions, travel time, and distance. Find the best route between two or more locations
solve_vehicle_routing
Takes an ArcGIS Orders JSON mapping string detailing the stops. Solve a Vehicle Routing Problem (VRP) for a fleet
suggest_geocoding
Use this to help users select valid addresses before performing a full geocode request. Get autocomplete suggestions for partial addresses or place names
suggest_location_bias
Get autocomplete suggestions biased towards a specific location
Example Prompts for ArcGIS in OpenAI Agents SDK
Ready-to-use prompts you can give your OpenAI Agents SDK agent to start working with ArcGIS immediately.
"What is the closest address to coordinates -117.19, 34.05?"
"Find the optimal driving route visiting stops -122.4,37.7 and -122.5,37.8."
"Resolve the coordinate location for 'Central Park' but restrict the search strictly to the USA."
Troubleshooting ArcGIS MCP Server with OpenAI Agents SDK
Common issues when connecting ArcGIS to OpenAI Agents SDK through the Vinkius, and how to resolve them.
MCPServerStreamableHttp not found
pip install --upgrade openai-agentsAgent not calling tools
ArcGIS + OpenAI Agents SDK FAQ
Common questions about integrating ArcGIS MCP Server with OpenAI Agents SDK.
How does the OpenAI Agents SDK connect to MCP?
MCPServerSse(url=...) to create a server connection. The SDK auto-discovers all tools and makes them available to your agent with full type information.Can I use multiple MCP servers in one agent?
MCPServerSse instances to the agent constructor. The agent can use tools from all connected servers within a single run.Does the SDK support streaming responses?
Connect ArcGIS with your favorite client
Step-by-step setup guides for every MCP-compatible client and framework:
Anthropic's native desktop app for Claude with built-in MCP support.
AI-first code editor with integrated LLM-powered coding assistance.
GitHub Copilot in VS Code with Agent mode and MCP support.
Purpose-built IDE for agentic AI coding workflows.
Autonomous AI coding agent that runs inside VS Code.
Anthropic's agentic CLI for terminal-first development.
Python SDK for building production-grade OpenAI agent workflows.
Google's framework for building production AI agents.
Type-safe agent development for Python with first-class MCP support.
TypeScript toolkit for building AI-powered web applications.
TypeScript-native agent framework for modern web stacks.
Python framework for orchestrating collaborative AI agent crews.
Leading Python framework for composable LLM applications.
Data-aware AI agent framework for structured and unstructured sources.
Microsoft's framework for multi-agent collaborative conversations.
Connect ArcGIS to OpenAI Agents SDK
Get your token, paste the configuration, and start using 10 tools in under 2 minutes. No API key management needed.