Pinpoint people or assets inside any building.
Claude
ChatGPT
Cursor
Gemini
Windsurf
VS Code
JetBrains
Vercel
Works with every AI agent you already use
…and any MCP-compatible client








Connect to your AI in seconds.
IndoorAtlas helps you manage and analyze indoor location services for commercial buildings. List venues, upload floor plans, and run positioning models from raw signal data.
Get full control over your building's digital twin by connecting it directly to any AI client.
What your AI can do
Upload floorplan geojson
Accepts and uploads a new floor map as a GeoJSON file, geo-referencing it to make it ready for accurate positioning overlays.
Create venue
Sets up a new building container in IndoorAtlas, requiring you to specify the name, entrance coordinates, and initial setup parameters.
Trigger map generation
Initiates the server-side computation that creates the positioning model for a specific floor plan using collected signal data.
List all physical venues in your organization and inspect a venue's detailed metadata, including its coordinate system and floor count.
Import new facility maps as GeoJSON files and correctly align them to real-world coordinates for accurate positioning overlays.
Run signal fingerprinting walk paths to check coverage and generate the necessary models that allow location tracking to work on a specific floor.
Retrieve full positioning session data, giving you timestamped coordinates to analyze where people spent their time or how often they moved through certain areas.
Calculate a device's estimated indoor position by submitting observed Wi-Fi signal strengths, useful when mobile SDK integration isn't possible.
Ask an AI about this
Compatible AI Apps
OAuth 2.0 CompatibleWaiting for input…
IndoorAtlas (Indoor Positioning) MCP: 10 Tools
These tools let you define physical spaces, map out facility blueprints, simulate signal tracking, and analyze movement data across entire buildings.
Make your AI actually useful.
Add this MCP to Claude, Cursor, or Windsurf and your AI stops guessing. It gets real tools to look things up, take action, and handle the stuff you keep doing by hand.
Start using IndoorAtlas (Indoor Positioning) on VinkiusUpload Floorplan Geojson
Accepts and uploads a new floor map as a GeoJSON file, geo-referencing it to make it ready for accurate positioning overlays.
Create Venue
Sets up a new building container in IndoorAtlas, requiring you to specify the name...
Trigger Map Generation
Initiates the server-side computation that creates the positioning model for a...
Get Fingerprint Paths
Retrieves the specific routes surveyors walked for calibration as GeoJSON, helping...
Get Session Data
Fetches the full track record of a single positioning session, including all...
Get Venue Details
Pulls detailed metadata on a specific venue, reporting its total mapped area, floor count, and current calibration status before deployment.
List Floorplans
Returns a list of every floor plan uploaded to the venue, detailing their dimensions, floor number, and whether mapping is ready for use.
List Positioning Sessions
Provides an indexed list of historical tracking sessions by returning IDs, start/end...
List Venues
Lists all buildings registered in your account, giving you the ID, name, and...
Position From Wifi Scan
Calculates an estimated indoor location by accepting observed Wi-Fi signal strengths...
Connect to your AI in seconds. Security and governance baked right in.
Pick your AI client below to get set up. Just create a Vinkius account, subscribe, and you're instantly up and running. We handle the entire backend infrastructure, delivering out-of-the-box support for HTTPS Streamable, SSE, and OAuth2—zero messy routing required.
Choose How to Get Started
Build a custom MCP for your own tools, or connect a ready-made integration from our catalog.
Build Your Own
Turn any API into an MCP. Import a spec, define Agent Skills, or deploy with MCPFusion.
- Import from OpenAPI, Swagger, or YAML specs
- Create Agent Skills with progressive disclosure
- Deploy to edge with MCPFusion framework
- Built in DLP, auth, and compliance on every call
- Real time usage dashboard and cost metering
- Publish to catalog or keep private
Make Your AI Do More
Start with IndoorAtlas (Indoor Positioning), then connect any of our 5,000+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 5,000+ others, all in one place
- Add new capabilities to your AI anytime you want
- Every connection is secured and compliant automatically
- Track usage and costs across all your servers
- Works with Claude, ChatGPT, Cursor, and more
- New servers added to the catalog every week
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.
VINKIUS INFRASTRUCTURE
Cloud Hosted
Managed infra
V8 Isolated
Sandboxed per request
Zero-Trust Proxy
No stored credentials
DLP Enforced
Policy on every call
GDPR Compliant
EU data residency
Token Compression
~60% cost reduction
Works with Claude, ChatGPT, Cursor, and more
The Model Context Protocol standardizes how applications expose capabilities to LLMs. Instead of operating in isolation, your AI gains direct access to external platforms, live data, and real-world actions through secure, standardized connections.
This connection provides 10 powerful capabilities that interface natively with Claude, ChatGPT, Cursor, and other compatible AI platforms. No middleware. No custom integration required.
Manually tracking movement across multiple building floors takes hours.
Right now, if you want to analyze where people moved through your campus over six months, you have to export data from the local monitoring system. You then copy those thousands of latitude/longitude points into a separate analysis tool and manually correlate them with floor plans and time stamps. It's tedious work involving dozens of tabs just to find out if people used the new elevator bank.
With this MCP, your agent handles the entire data pipeline. You tell it what you want—say, 'Show me traffic density near the main atrium.' The system pulls all necessary positioning session data, correlates it with every floor plan uploaded, and delivers the analysis directly to you.
IndoorAtlas (Indoor Positioning) MCP gives you full control over your location data.
The manual process of setting up a new wing involves submitting raw GeoJSON files, triggering the radio map generation in one window, and then manually verifying that all coordinates are properly anchored to real-world points. This is an iterative nightmare.
Now, you upload your floor plan via `upload_floorplan_geojson`, trigger the model computation with `trigger_map_generation` through a single conversation thread, and have the system handle the rest of the complex geometry alignment for you.
What your AI can actually do with this
You can take complete control of smart building infrastructure without needing a dedicated GIS team on retainer. This MCP connects your entire facility management system—from floor plan storage to real-time tracking analysis—to your agent. You start by defining the physical space, listing all available venues and uploading precise GeoJSON floor plans.
Once the map is set up, you can trigger the complex radio map generation process using signal data. From there, your agent tracks anything inside: determine a device's location simply from an incoming Wi-Fi scan or retrieve historical paths of people over weeks. You’ll find that Vinkius makes connecting these specialized services simple; instead of switching between three different platforms to analyze occupancy, you handle everything through natural conversation.
019d75b9-2f40-71f3-96aa-134d54050017 Here's how it actually works
The bottom line is that this MCP turns static architectural drawings into dynamic, actionable data layers for your agent to read and analyze.
First, use the create_venue tool to define the building name and its entrance coordinates.
Next, upload floor plans using upload_floorplan_geojson, then run the map generation process with trigger_map_generation. The system computes the positioning model from your signal data and geometry.
After setup, you can request historical tracking via list_positioning_sessions or get a current estimate by calling position_from_wifi_scan.
Who is this actually for?
This connector targets professionals who manage large physical spaces. Think of the facilities manager who needs to know which wing of a hospital is seeing low foot traffic, or the security analyst tracking movement patterns in a high-value warehouse.
Auditing building usage by analyzing positioning session data and assessing calibration coverage across multiple floors.
Managing geo-referencing for complex indoor maps, ensuring all uploaded floor plans align perfectly with real-world coordinates.
Integrating indoor location services into automated workflows and monitoring the status of various mapped venues using detailed metadata calls.
What Changes When You Connect
Audit Building Usage: Instead of relying on manual counts, use get_session_data to analyze occupancy patterns and understand dwell times across the facility.
Quickly Map New Areas: Upload a plan with upload_floorplan_geojson, then initiate positioning models using trigger_map_generation—all without complex GIS software.
Know Your Space: Use list_venues to quickly find all registered buildings and check their status before starting any new project or analysis.
Determine Location Remotely: When you can't use a mobile app, submitting raw signals via position_from_wifi_scan still gives your agent an estimated coordinate.
Full Site Overview: By calling get_venue_details, you get immediate confirmation of the building’s total mapped area and calibration completeness.
See it in action
Optimizing Retail Flow
A retail operations manager needs to know if seasonal displays are drawing people to a specific corner. They run list_positioning_sessions, identify the high-traffic times, and then use that data to reposition merchandise for better visitor flow.
Onboarding New Campus Wings
A developer gets a new wing built and needs it mapped. They first run list_venues to confirm the site exists, then call create_venue, upload the plans with upload_floorplan_geojson, and trigger map generation.
Assessing Safety Risks
The safety officer suspects a certain utility closet is rarely checked. They run get_fingerprint_paths for that area to see if the calibration coverage was adequate, ensuring future tracking will work there.
The honest tradeoffs
Assuming GPS works indoors
Trying to get accurate location data in a concrete-heavy hospital basement using only standard GPS coordinates.
Don't use general GPS tools. Instead, you must first define the space by calling create_venue, then provide local signals and floor plans via upload_floorplan_geojson so your agent can calculate position from Wi-Fi scans.
Skipping map generation
Uploading a beautiful new GeoJSON floor plan but never running the computational model.
This is a common mistake. You must always follow upload_floorplan_geojson with trigger_map_generation. The positioning data won't work until that process completes.
Only checking for existence
Calling list_venues and assuming the venue is fully ready for use.
Check the full status by calling get_venue_details. This ensures you see metrics like total mapped area and calibration status before building any workflows.
When It Fits, When It Doesn't
Use this MCP if your core problem revolves around mapping, tracking, or analyzing activity within a defined physical structure (e.g., a hospital, factory, mall). It's built for location intelligence where GPS fails.
Don't use it if you just need to track assets outdoors; standard GPS tools are fine then. Also, don't use it if your only goal is basic floor plan viewing—you still need the signal data and map generation steps first. If you only have a spreadsheet of coordinates, you might be better served by a simple database tool rather than one requiring full facility mapping.
Questions you might have
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.
How does using the list_venues tool help me discover all potential locations for mapping? +
It returns an array of every registered facility, providing their IDs, names, and geographic coordinates. Always call this first to confirm which buildings are ready before attempting to retrieve specific floor plan or session data.
When I use upload_floorplan_geojson, what specific GeoJSON structure must the file have? +
The uploaded document needs to be a valid GeoJSON that geo-references the indoor map image. This process ties the digital floor plan directly to real-world coordinates, making accurate positioning possible.
If I call get_session_data for years of records, how big is the output data set? +
The tool returns a full position trace as thousands of timestamped fixes. Be aware that your AI client needs robust memory handling to process potentially massive amounts of positional coordinate data.
What should I check if there are gaps in my signal mapping using get_fingerprint_paths? +
The output GeoJSON shows all recorded walk paths. You analyze this data layer to pinpoint specific areas or zones that lack coverage and require additional physical surveying runs for better accuracy.
After listing floor plans with list_floorplans, what's the necessary next step to actually enable positioning? +
Listing only provides metadata. You must use those IDs to upload the plan via upload_floorplan_geojson and then explicitly trigger map generation before any positioning data will work.
We've already built the connector for IndoorAtlas. Just plug in your AI agents and start using Vinkius.
No hosting. No infrastructure. No complex setup.
All 10 tools are live and waiting.
You're up and running in seconds.
Vinkius gives your AI agents access to the full catalog of app connectors, all fully managed, secure, and enterprise-ready. One subscription, every tool you need.
Built, hosted, and secured by Vinkius. You just connect and go.