# IndoorAtlas MCP for AI Agents AI Agent Connect > IndoorAtlas MCP lets you manage indoor positioning for smart buildings. Use it to list venues, upload floor plans, trigger radio map generation, and pull session data for occupancy analytics. It connects your IndoorAtlas account to your AI agent so you can manage complex building layouts and positioning data through a chat interface. ## Overview - **Category:** iot-hardware - **Price:** Free - **Endpoint:** https://edge.vinkius.com/vk_preview_G0vuBwWUnv44gPThdIn5uIk7VpxqbtULEOzfoENF/ai-agent-connect - **Tags:** indoor-positioning, mapping, smart-buildings, location-services, floorplan-analysis, geolocation ## Description IndoorAtlas MCP lets you manage smart building infrastructure through a chat interface. Instead of digging through complex GIS software or navigating multiple dashboards, you can ask your AI agent to handle the heavy lifting of indoor positioning. You can pull up venue metadata, upload new floor plans, and trigger the radio map generation process without switching tabs. If you need to know if a specific area is covered, you can ask the agent to check the calibration walk paths. It’s about turning your positioning data into a conversational tool for building operations. Because Vinkius makes it easy to connect this to your favorite tools, you can move from manual data entry to real-time spatial management in seconds. ## Tools ### list_positioning_sessions Get a paginated list of historical indoor positioning sessions. Use this to analyze occupancy, dwell times, and path optimization. ### upload_floorplan_geojson Upload a new floor plan as a GeoJSON document to a venue. This lets you overlay indoor maps onto real-world coordinates for accurate positioning. ### create_venue Create a new indoor venue with a name, entrance coordinates, and configuration. This serves as the top-level container for all your floor plans and positioning data. ### get_fingerprint_paths Retrieve the GeoJSON walk paths recorded by surveyors during calibration. Use this to find areas that need more signal mapping for better accuracy. ### get_session_data Pull the full positioning trace for a specific session. It includes timestamped coordinates and floor transitions for behavioral analysis. ### get_venue_details Get the metadata for a specific venue, like its floor count and calibration status. This helps you inspect a building before deploying wayfinding features. ### list_floorplans List all floor plans for a venue with their dimensions and map status. It shows you which levels are ready for positioning. ### list_venues List all venues in your organization with their names and coordinates. This helps you quickly find a specific building to manage. ### trigger_map_generation Start the radio map generation process for a specific floor. It computes the positioning model from your signal fingerprints and floor geometry. ### position_from_wifi_scan Get estimated coordinates and floor levels from a Wi-Fi scan. This is perfect for location tracking when you can't use a mobile SDK. ## Prompt Examples **Prompt:** ``` Show me the status of all the venues in our organization. ``` **Response:** ``` I've found 3 venues in your organization: | Venue Name | Status | Calibration | | :--- | :--- | :--- | | Corporate HQ | Mapped | Complete | | Retail Mall | Mapped | In Progress | | Logistic Warehouse | Mapped | Complete | Which one would you like to see floor plans for? ``` **Prompt:** ``` Are there any gaps in the calibration for the 2nd floor of the Warehouse? ``` **Response:** ``` I've retrieved the calibration walk paths for the Warehouse (Floor 2). **Coverage Analysis:** * **Main Loading Dock:** 95% coverage * **Aisle 4-10:** 88% coverage * **Storage Zone B:** 42% coverage It looks like **Storage Zone B** needs more fingerprinting to ensure accurate positioning. ``` **Prompt:** ``` Summarize the occupancy for the Corporate HQ today. ``` **Response:** ``` I've analyzed the 12 positioning sessions recorded today for the Corporate HQ: * **Total Active Sessions:** 12 * **Peak Occupancy:** 2:00 PM - 4:00 PM * **Average Dwell Time:** 42 minutes * **Most Active Area:** Conference Room B Would you like to see the full trace data for the longest session? ``` ## Capabilities ### List all registered indoor venues Retrieve a complete list of venues with their geographic metadata. ### Upload new floor plans Add floor plans to a venue using map files for accurate positioning. ### Trigger radio map generation Start the process to create positioning models from signal data. ### Retrieve positioning session traces Pull historical data for behavioral analysis and occupancy studies. ### Get coordinates from Wi-Fi scans Determine indoor location from Wi-Fi signal strengths. ### Inspect calibration walk paths Check surveyor routes to identify gaps in signal mapping. ## Use Cases ### Mapping Audit A manager wants to see if the 'Retail Mall' is mapped correctly. They ask the agent to list venues and check the calibration paths for floor 3. ### Floor Plan Update A developer needs to add a new floor. They ask the agent to create a venue and then upload the floor plan file. ### Occupancy Analysis An ops lead wants to know why people are clustering in one area. They ask the agent to pull the session data for today's busiest period. ### Signal Debugging A technician needs to know why a specific area has poor accuracy. They use the agent to retrieve fingerprint paths and see if the surveyor missed a hallway. ## Benefits - Stop manual GIS work by using upload_floorplan_geojson to handle map files through simple chat commands. - Get instant answers on building status using get_venue_details to check floor counts and calibration. - Analyze building flow quickly with list_positioning_sessions to see how people actually move through your space. - Identify signal dead zones immediately with get_fingerprint_paths to see exactly where surveyors walked. - Simplify multi-floor management by using list_floorplans to see the readiness of every level at once. - Enable location services for any device using position_from_wifi_scan to get coordinates without complex SDK integration. ## How It Works The bottom line is you get a conversational interface for complex indoor positioning infrastructure. 1. Subscribe to the Connector and grab your IndoorAtlas API Key. 2. Connect the Connector to your preferred AI client like Claude or Cursor. 3. Start asking your agent to manage venues, floor plans, and analytics. ## Frequently Asked Questions **How does the IndoorAtlas MCP help with floor plans?** It allows you to upload floor plan files and manage the radio map generation process through a chat interface. You can quickly add new levels or update existing ones without opening complex GIS software. **Can I use this to see where people are walking in my building?** Yes, you can pull historical positioning session data to see exactly how people move through your space. This is great for identifying bottlenecks or analyzing occupancy patterns. **What happens when I upload a floor plan?** The Connector uploads the map file to your venue and allows you to trigger the map generation process. This creates the positioning model needed for your AI agent to understand the floor layout. **Can I get location data without a mobile app?** Yes, you can use the Wi-Fi scan tool to get estimated coordinates and floor levels. This is a great way to get location data when you don't have a mobile SDK integrated. **How do I check if my building is properly calibrated?** You can ask your agent to inspect the calibration walk paths. It will show you the routes surveyors took and highlight any areas that need more signal mapping. **Is this for managing multiple buildings?** Absolutely. You can list all venues in your organization and manage floor plans, metadata, and analytics for every building in your portfolio from one place. **How do I start the map generation process for a new floor plan?** Use the `trigger_map_generation` tool 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. **Can I determine a position using Wi-Fi scans through my agent?** Yes. The `position_from_wifi_scan` tool 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. **How can I analyze visitor traffic patterns in our building?** Use the `list_positioning_sessions` tool to retrieve historical traces. Your agent can help you analyze occupancy patterns and dwell times by processing the timestamped coordinate fixes from past sessions.