How to Use the IndoorAtlas (Indoor Positioning) MCP in OpenAI Agents SDK

Q: Can my OpenAI Agents SDK agent automatically handle floorplan alignment issues?

Yes, by combining the tools. Your agent can call listfloorplans to check the geo-alignment status of a specific level. If it detects misalignment, it uses uploadfloorplangeojson to correct the coordinates.

Q: How does the agent know when a radio map is ready for positioning?

The agent calls listfloorplans to inspect the map generation readiness flag. If the flag is false, the agent executes triggermapgeneration and polls until the status changes to complete.

Build production-ready spatial agents that track indoor assets and manage maps using the OpenAI Agents SDK.

See Vinkius in Action

Works with every AI agent you already use

…and any MCP-compatible client

MCP Servers - Free for Subscribers

Connect IndoorAtlas (Indoor Positioning) MCP to OpenAI Agents SDK

Create your Vinkius account to connect IndoorAtlas (Indoor Positioning) 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 IndoorAtlas (Indoor Positioning) with OpenAI Agents SDK

Ask AI about this MCP

ChatGPT

Claude

Perplexity

Automate venue deployment and map calibration

The `create_venue` tool lets your OpenAI agent set up a new building container with exact entrance coordinates in your IndoorAtlas account. You can instantly pass this off to an upload agent that uses `upload_floorplan_geojson` to geo-reference your floor maps. Once the files are in place, the agent triggers `trigger_map_generation` to compile the radio positioning model. Because OpenAI Agents SDK handles async tasks natively, your agent tracks the map generation status in the background without blocking other operations.

Track real-time assets with guardrailed scans

The `position_from_wifi_scan` tool calculates real-world coordinates and floor levels directly from raw Wi-Fi access point scans. OpenAI Agents SDK enforces runtime guardrails, ensuring your agent never requests coordinates without a valid signal payload. If a scan returns weak signals, the agent shifts to checking the physical environment. By calling `get_venue_details`, it verifies the geographic anchor and floor counts to confirm the system's spatial boundaries.

Analyze historical tracking data with this MCP Server

The `list_positioning_sessions` tool retrieves historical tracking data, giving your OpenAI agent access to exact session timestamps and device details. The agent uses this raw data to trace foot traffic patterns across different dates. For deeper spatial analysis, the agent calls `get_session_data` to extract the complete sequence of coordinate fixes and floor transitions. You can view these raw data transitions directly inside your OpenAI tracing dashboard.

Setup guide

Set up IndoorAtlas (Indoor Positioning) 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 IndoorAtlas (Indoor Positioning) tools at runtime.
3

Create your Agent

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

Run the agent

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

Install the package and configure the HTTP server parameters with your endpoint. Pass the server instance directly to the Agent constructor using the mcp_servers argument. The SDK automatically discovers the ten indoor positioning tools.

Yes, by combining the tools. Your agent can call `list_floorplans` to check the geo-alignment status of a specific level. If it detects misalignment, it uses `upload_floorplan_geojson` to correct the coordinates.

Yes. You can design one agent to monitor real-time positions using `position_from_wifi_scan` and hand off to a diagnostics agent if signal accuracy drops. The diagnostics agent can then pull `get_fingerprint_paths` to check calibration coverage.

The agent calls `list_floorplans` to inspect the map generation readiness flag. If the flag is false, the agent executes `trigger_map_generation` and polls until the status changes to complete.

All coordinate traces and floor transitions are processed inside an isolated V8 sandbox. The server uses ephemeral memory, meaning no raw coordinate history is stored on our servers.

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