An astronaut overseeing a futuristic data hub
Download PDFMarkdown Version

Connect Indooratlas Indoor Positioning to ChatGPT and Claude

Set it up once and it works in ChatGPT, Claude, Cursor, and any other client you love. It all runs safely in the background, so you can relax and focus on what really matters. Control your smart building infrastructure through your AI agent.

Ask AI about this Connector

Developed, maintained, and hosted by Vinkius.

MCP VERIFIED · PRODUCTION READY · VINKIUS GUARANTEED

Waiting for input…

Works with modern AI clients that support MCP, including ChatGPT, Claude, Cursor, and more.

ChatGPTClaudeCursorPerplexityGeminiMicrosoft CopilotRaycastMeta AI

Your AI does the work. We keep it safe and sound.

No other AI tool gives you this. Your workflow runs in the client you already love, your account stays protected, and you decide what the agent can and cannot do. It is the whole reason to make the switch.

Each Connector lives inside our infrastructure, the same place where your workflow runs. The three things below are already part of it, working quietly in the background so you never have to think about them. Nothing to add, nothing to set up, nothing to worry about.

A futuristic MCP client docking bay
V8 Isolate01

Each Connector runs inside its own sealed environment.

Each Connector runs inside its own sealed V8 runtime — no access to your files, your system, or other servers. A Connector never sees past its own request.

Kill Switch02

One switch stops every agent. Instantly.

One action deactivates every Connector, revokes every token, and ends every session at once. AI Governance keeps the record.

FinOps per User03

Spending limits that pause instead of surprise.

Every user keeps their own connections and credentials, isolated from everyone else. Anything that would cross your spending limit is held for your approval, not billed.

Three controls, built into the layer your AI connects through.

Curated set · 10 capabilities

We ship only the actions that matter.

Capability set01 / 03

01-04

4 capabilities in this set.

Part of 10 available through IndoorAtlas.

  1. 01

    List positioning sessions

    This capability returns a paginated list of historical indoor tracking sessions. Use it to pull session IDs, timestamps, and device info for occupancy or path analysis.

  2. 02

    Get fingerprint paths

    This capability retrieves GeoJSON LineString features representing calibration paths. It helps you identify areas where you need more fingerprinting to improve accuracy.

  3. 03

    Upload floorplan geojson

    This capability uploads a new GeoJSON floor plan to a specific venue. It handles the geo-referencing required to align your indoor map with real-world coordinates.

  4. 04

    Get venue details

    This capability pulls metadata for a specific venue. You can check its geographic anchor point, floor count, and current calibration status.

Capability set02 / 03

05-07

3 capabilities in this set.

Part of 10 available through IndoorAtlas.

  1. 05

    List floorplans

    This capability lists all floor plans within a venue. It provides floor numbers, dimensions, and tells you if radio map generation is finished.

  2. 06

    List venues

    This capability returns a list of all registered indoor venues in your organization. Use it to find venue IDs before requesting floor or session data.

  3. 07

    Create venue

    This capability creates a new top-level venue container. You specify the building name and the geographic coordinates for the entrance.

Capability set03 / 03

08-10

3 capabilities in this set.

Part of 10 available through IndoorAtlas.

  1. 08

    Get session data

    This capability retrieves the full timestamped position trace for a specific session. It includes coordinate fixes, floor transitions, and accuracy metrics.

  2. 09

    Position from wifi scan

    This capability calculates an indoor position based on Wi-Fi signal strengths. It returns estimated latitude, longitude, and floor level.

  3. 10

    Trigger map generation

    This capability starts the asynchronous radio map generation process. You must run this after uploading a floor plan to enable positioning on that floor.

Real work

What teams actually run

01

Calibration Auditing

Identify gaps in your signal mapping by reviewing GeoJSON fingerprint paths.

02

Occupancy Analysis

Study how visitors move through a facility using timestamped position traces.

03

Automated Mapping

Upload floor plans and trigger map generation without using a web dashboard.

04

Server-Side Positioning

Get indoor coordinates from Wi-Fi scans when you can't use a mobile SDK.

Automate a task

Put IndoorAtlas to work on one thing.

Step-by-step automations your AI runs through this Connector: the workflow, the prompts to start with, and the exact capabilities behind each move.

One connector, every AI

IndoorAtlas works with the most popular AI clients.

These are the most popular clients, each with a step-by-step guide: one link, set up once, with governance and visibility built in. And because everything runs on the MCP standard, the same connection also works in any other compatible client — nothing to rebuild.

ClaudeClaudeChatGPTChatGPTGeminiGeminiPerplexityPerplexityGrokGrokMicrosoft CopilotMicrosoft CopilotCursorCursorVS CodeVS CodeWindsurfWindsurfJetBrainsJetBrainsClineClineLangChainLangChainVercel AI SDKVercel AI SDKLovableLovableZ.aiZ.aiRaycastRaycastQwen CodeQwen CodeKimi CodeKimi CodeLe ChatLe Chat

Building your own app? The connector is yours to use.

You don't need a client to put IndoorAtlas to work: the same hosted connection plugs into your own applications and agent code, with the same governance on every request. Build with it, chat with it — one connection for both.

Observed, not estimated

968ms average. Fast in production.

IndoorAtlas is checked daily against the live service.

Daily averagePeak 1252ms
Oct 3Today
Fastest day
717ms
Slowest day
1252ms
14-day trend
Improving-11%

Connect your client

One URL. Every client.

Activate the Connector, copy your link, and paste it into the client you already use. 10 capabilities arrive ready to run.

Preview access · not provider authentication

The vk_preview_* token belongs to Vinkius preview infrastructure. It lets Claude discover and display the capabilities of IndoorAtlas, so you can see the experience inside your AI.

It does not authenticate your account with IndoorAtlas. Actions requiring credentials or live account data may not run until you activate the Connector and authorize the service.

IndoorAtlas Connector

You're all set. Choose your MCP client and follow the setup instructions.

Connector linkhttps://edge.vinkius.com/vk_preview_G0vuBwWUnv44gPThdIn5uIk7VpxqbtULEOzfoENF/mcp

Claude Desktop

Follow the steps below to connect in seconds.

  1. 1In Claude Desktop, open Settings → Connectors.
  2. 2Click “Add custom connector” and paste the connector link above as the remote MCP server URL.
  3. 3Click Add and start a new chat — IndoorAtlas capabilities are ready to use.
Configuration · claude_desktop_config.jsonCopy
{
  "mcpServers": {
    "indooratlas-indoor-positioning-mcp": {
      "url": "https://edge.vinkius.com/vk_preview_G0vuBwWUnv44gPThdIn5uIk7VpxqbtULEOzfoENF/mcp"
    }
  }
}
  • Claude
  • ChatGPT
  • Cursor
  • VS Code
  • Windsurf
  • Claude Code
  • JetBrains
  • Cline

Step-by-step instructions for each client are in the guide. How to connect

Guided setup for Claude? Set up IndoorAtlas in Claude and other AIs

See all the AI clients this connector works with ↑

Who it's for

Built for the work IndoorAtlas owners hand off.

This MCP is built for professionals managing large-scale indoor location environments.

  • 01

    Smart Building Developers

    They use the agent to integrate location services and monitor venue calibration.

  • 02

    GIS Analysts

    They manage floor plans and geo-referencing through natural language instead of manual GIS capabilities.

  • 03

    Operations Managers

    They audit occupancy data and positioning traces to optimize building flow.

FAQ

Questions IndoorAtlas owners ask.

  • 01

    How do I enable positioning on a new floor?

    After you upload a floor plan using the upload capability, you must trigger the map generation process. This is an asynchronous task that creates the positioning model.

  • 02

    Can I use this with my existing IndoorAtlas account?

    Yes, you just need to provide your IndoorAtlas API Key to the MCP after connecting.

  • 03

    What kind of data can my AI agent retrieve?

    Your agent can access venue metadata, floor plan details, historical positioning sessions, and fingerprinting walk paths.

  • 04

    How does the Wi-Fi positioning work?

    You can submit Wi-Fi access point scans to the agent, which then uses the Positioning API to return coordinates and floor levels.

  • 05

    Which AI clients are compatible?

    This MCP works with any compatible client, including Claude, Cursor, and Windsurf.

  • 06

    How do I start the map generation process for a new floor plan?

    Use the trigger_map_generation capability with your Floorplan ID. This initiates the server-side computation that creates the positioning model. It's a critical step before indoor positioning can work on that level.

  • 07

    Can I determine a position using Wi-Fi scans through my agent?

    Yes. The position_from_wifi_scan capability allows you to submit observed Wi-Fi signal strengths. Your agent will return estimated coordinates and floor level, which is perfect for server-side positioning logic.

  • 08

    How can I analyze visitor traffic patterns in our building?

    Use the list_positioning_sessions capability to retrieve historical traces. Your agent can help you analyze occupancy patterns and dwell times by processing the timestamped coordinate fixes from past sessions.

Explore

More in Iot Hardware

Suggestions

Connect IndoorAtlas to Claude, Cursor, ChatGPT & more