How to Use the Mapflow MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent poll for Mapflow processing status?

Yes, the agent uses getprocessingstatus in a basic loop to check the job state. Once the status reads success, the agent pulls down the GeoJSON vector files using getprocessingresult.

Q: How do Mapflow and OpenAI Agents SDK handle model selection?

The server exposes listmodels which returns the specific IDs for building, road, and forest extraction models. Your agent reads these parameters to pass the correct model ID to createprocessing.

Q: Can I run multiple extractions concurrently?

You can initiate multiple jobs by calling createprocessing repeatedly. Use listprocessings to track the state of all active runs across your workspace.

Run automated geospatial extraction pipelines directly inside your OpenAI Agents SDK workflows using our MCP server.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect Mapflow MCP to OpenAI Agents SDK

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

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Run satellite imagery extraction with OpenAI Agents SDK

`create_processing` starts an automated run to extract buildings, roads, and vegetation from raw satellite coordinates. Your agent selects the exact area, fires off the job, and receives a tracking ID instantly without manual GIS intervention. Managing these runs requires constant tracking. The agent uses `get_processing_status` to poll for completion, then grabs the finalized vector data using `get_processing_result` once the run finishes.

Mapflow MCP Server model discovery

`list_models` exposes the available neural network configurations optimized for specific geographic features. Your agent reads this list to decide whether to run a building footprint extraction or a road network analysis. This dynamic selection prevents hardcoded failures. By matching the target terrain to the correct model, your autonomous system maintains high accuracy across different urban density profiles.

Keep runs organized with project workspaces

`create_project` sets up an isolated workspace for grouping related spatial analyses. Your agent organizes raw inputs by client or region, keeping the entire pipeline clean and traceable. Tracking active jobs across these workspaces is straightforward. The agent calls `list_projects` and `list_processings` to audit what runs are active, helping you control API costs and monitor throughput.

Setup guide

Set up Mapflow 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 Mapflow tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the SDK and register the Mapflow MCP server using the streamable HTTP transport parameter. Your agent automatically discovers the spatial tools during initialization, letting you run extractions inside standard agent run loops.

Yes, the agent uses `get_processing_status` in a basic loop to check the job state. Once the status reads success, the agent pulls down the GeoJSON vector files using `get_processing_result`.

The server exposes `list_models` which returns the specific IDs for building, road, and forest extraction models. Your agent reads these parameters to pass the correct model ID to `create_processing`.

You can initiate multiple jobs by calling `create_processing` repeatedly. Use `list_processings` to track the state of all active runs across your workspace.

Vinkius runs the Mapflow MCP server inside an isolated V8 sandbox. Your coordinates and processed GeoJSON shapes pass directly to the API, meaning no imagery metadata is stored on Vinkius servers after the request completes.

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