IndoorAtlas MCP. Analyze building blueprints and track indoor movement.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Just plug in your AI agents and start using Vinkius.
IndoorAtlas (Indoor Positioning) MCP Server. Manage smart building data by listing venues, uploading floorplans, and analyzing positioning sessions. Connect your AI client to IndoorAtlas to handle everything from geo-referencing and Wi-Fi positioning to full occupancy pattern analysis.
Use it to audit building infrastructure and optimize visitor flows without complex GIS software.
What your AI agents can do
Create venue
Sets up a new indoor venue by specifying the building name, entrance coordinates, and initial positioning parameters.
Get fingerprint paths
Retrieves the GeoJSON walk paths used for calibration, showing where signal data was collected for a specific floor plan.
Get session data
Fetches the complete, timestamped positioning trace for a specific session, including coordinate fixes and accuracy metrics.
List all registered venues and retrieve detailed configuration data, including floor count and geographic anchors.
Upload GeoJSON floor plans and align them to real-world coordinates for accurate positioning overlays.
Retrieve full positioning traces and list historical sessions to measure dwell times and path patterns.
Calculate estimated indoor coordinates and floor levels using raw Wi-Fi signal strength data.
Retrieve the walk paths recorded during calibration to check coverage and pinpoint areas lacking signal data.
Ask AI about this MCP
Supported MCP Clients
Gemini Waiting for input…
019d75b9create venue
Sets up a new indoor venue by specifying the building name, entrance coordinates, and initial positioning parameters.
019d75b9get fingerprint paths
Retrieves the GeoJSON walk paths used for calibration, showing where signal data was collected for a specific floor plan.
019d75b9get session data
Fetches the complete, timestamped positioning trace for a specific session, including coordinate fixes and accuracy metrics.
019d75b9get venue details
Returns detailed metadata for a venue, including its geographic anchor point, floor count, and total mapped area.
019d75b9list floorplans
Lists all uploaded floor plans for a venue, detailing their dimensions and whether the map generation process is complete.
019d75b9list positioning sessions
Lists historical tracking sessions, providing IDs and time ranges for occupancy analysis and path replay.
019d75b9list venues
Lists all indoor venues registered in your account, providing IDs, names, and general configuration status.
019d75b9position from wifi scan
Estimates the indoor coordinates and floor level using observed Wi-Fi signal strengths from a scan.
019d75b9trigger map generation
Starts the server-side computation to create a positioning model from floor plan geometry and signal data.
019d75b9upload floorplan geojson
Uploads a new GeoJSON floor plan, geo-referencing the image to real-world coordinates for accurate positioning.
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 4,700+ other servers whenever your AI needs more. One click, no limits.
- Use this MCP plus 4,700+ 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
What you can do with this MCP connector
You're gonna manage smart building data the easy way. Connect your AI client to this IndoorAtlas server, and you'll get tools to handle everything from mapping venues to tracking people inside a building. You can use your agent to audit building infrastructure and figure out visitor flow without needing complex GIS software.
Identify and manage physical locations
- You can list all venues registered in your account using
list_venuesto get IDs, names, and configuration status. To get deep details on a specific location, runget_venue_details; that'll give you the geographic anchor point, floor count, and total mapped area. You can also usecreate_venueto set up a new indoor venue by specifying the building name, entrance coordinates, and initial positioning parameters. - You can list all uploaded floor plans for a venue with
list_floorplans, which tells you the dimensions and whether map generation is done. To add a blueprint, useupload_floorplan_geojsonto upload a new GeoJSON floor plan, geo-referencing it to real-world coordinates for accurate positioning.
Analyze movement data and occupancy
- You can list historical tracking sessions using
list_positioning_sessions, which gives you IDs and time ranges for later analysis. To get the actual movement data, useget_session_datato fetch the complete, timestamped positioning trace for a specific session, including coordinate fixes and accuracy metrics. You can figure out dwell times and path patterns by reviewing this data. You can also analyze the paths used for calibration by runningget_fingerprint_paths, which retrieves the GeoJSON walk paths for a specific floor plan.
Determine live indoor location
- When you get a raw Wi-Fi signal scan, you can use
position_from_wifi_scanto estimate the indoor coordinates and floor level. This tells you where things are right now.
Audit and improve signal mapping
- To start the process of building the positioning model, you must run
trigger_map_generation, which starts the server-side computation using floor plan geometry and signal data. You can check the coverage by retrieving the walk paths recorded during calibration usingget_fingerprint_paths.
How IndoorAtlas MCP Works
- 1 First, use
list_venuesto find the ID of the building you need to work on. - 2 Next, use
get_venue_detailsto inspect the venue's current mapping status and floor count. - 3 Finally, use
list_floorplansto get the IDs of all available floor plans and determine which ones need map generation.
The bottom line is you get a structured, conversational way to manage the entire lifecycle of indoor location data, from initial blueprint upload to live occupancy analysis.
Who Is IndoorAtlas MCP For?
This is for smart building developers and operations engineers who can't afford to treat their building infrastructure as a collection of separate, siloed systems. If your job requires knowing exactly how people move through a physical space, you need this. You're the person who needs to move beyond simple heatmaps and start optimizing flow.
Integrates indoor location services into AI agents, using the server to monitor venue calibration status and map coordinates.
Manages complex indoor floor plans and coordinates geo-referencing through natural language, skipping complex GIS software workflows.
Audits occupancy analytics and positioning session data to identify bottlenecks and improve visitor flow in real time.
What Changes When You Connect
- See the full scope of your building with
list_venuesandget_venue_details. You instantly get the building's floor count, anchor point, and total mapped area. - Upload blueprints and get them aligned with reality. Use
upload_floorplan_geojsonto map new GeoJSON files to real-world coordinates. - Understand how people move.
list_positioning_sessionspulls a history of tracks, letting you study dwell times and common paths. - Get a live location estimate from raw data.
position_from_wifi_scancalculates coordinates and floor levels from simple Wi-Fi signal readings. - Audit the data quality.
get_fingerprint_pathsshows the exact walk paths collected during calibration, highlighting where more signal data is needed. - Keep your maps current. You can trigger model updates with
trigger_map_generationonce you've uploaded a new floor plan.
Real-World Use Cases
Auditing a newly mapped facility
An operations manager needs to check if a new wing is fully mapped. They ask their agent to run list_venues first, then use get_venue_details to confirm the facility's total mapped area and floor count. They follow up with list_floorplans to ensure every floor has an uploaded blueprint.
Analyzing retail traffic flow
A retail analyst wants to optimize layout. They ask the agent to list recent sessions using list_positioning_sessions. The agent fetches the data, and the analyst reviews the path data to find bottlenecks and areas where people tend to linger.
Setting up a new building location
A developer needs to start mapping a new site. They use create_venue to define the building's scope, then upload_floorplan_geojson to add the first blueprint, and finally trigger_map_generation to make the data usable.
Emergency response planning
A safety officer needs to know the best routes. They run get_fingerprint_paths to verify calibration coverage across all floors, ensuring that the entire facility is mapped for accurate emergency navigation.
The Tradeoffs
Assuming all data is ready
Trying to run get_session_data without first checking the venue status. This fails because positioning models haven't been generated, returning an empty set.
→
First, use list_venues to confirm the venue exists. Then, use list_floorplans and trigger_map_generation to ensure the positioning model is ready before requesting session data.
Treating data as static
Manually updating a floor plan and forgetting to update the system. The data remains old, leading to inaccurate positioning.
→
Always use upload_floorplan_geojson for new blueprints, followed immediately by trigger_map_generation to make the system compute the new positioning model.
Mixing up data types
Using get_fingerprint_paths when you actually need occupancy counts. The path data shows movement routes, not how many people were in a zone.
→
To count people and measure time spent, use list_positioning_sessions to get the session list, and then request the full trace with get_session_data.
When It Fits, When It Doesn't
Use this server if your core business problem is spatial. You need to know not just where a building is, but how people move through it. Use it when you need to correlate Wi-Fi signals to physical coordinates and analyze flow patterns. Don't use it if your data problem is simpler, like just needing a list of addresses or a single piece of static metadata; those systems suffice. If you only need to read a floorplan's dimensions without linking it to a live signal model, you might only need list_floorplans. But if you need to make that blueprint actionable for positioning, this server is required.
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 server provides 10 capabilities that interface natively with Claude, ChatGPT, Cursor, and any MCP client. No middleware. No custom integration required.
Available Capabilities
Mapping a building used to mean hiring expensive GIS teams and weeks of manual data entry.
Today, getting a functional indoor map involves a massive manual process. You gather blueprints, then hire surveyors to walk the entire site, collecting signal data point by point. You then feed all this data into proprietary, complex GIS software. It's slow, costly, and the resulting map is always a snapshot, not a live model.
With the IndoorAtlas MCP Server, you describe the need to your agent. It handles the whole sequence—from uploading the GeoJSON blueprint to triggering the complex map generation process—and gives you a usable positioning model. You get actionable data, not just a static image.
IndoorAtlas MCP Server: Get real-time, analyzed position data.
You no longer have to copy raw Wi-Fi logs into a spreadsheet and manually calculate coordinates. You simply tell your agent to use `position_from_wifi_scan`, and it returns the estimated coordinates and floor level. If you need the full history, you run `list_positioning_sessions` and then `get_session_data` to get the full trace.
The difference is scale. Instead of working with single data points, your agent processes entire session traces, giving you a complete behavioral picture of the space.
Common Questions About IndoorAtlas MCP
How do I start mapping a new building using the IndoorAtlas MCP Server? +
Start by calling create_venue with the building name and coordinates. Next, use upload_floorplan_geojson to add the blueprint. Finally, run trigger_map_generation to create the necessary positioning model.
What is the difference between `get_fingerprint_paths` and `get_session_data`? +
get_fingerprint_paths shows the routes surveyors walked to collect signal data (calibration paths). get_session_data shows the actual path of a device or person that moved through the building.
Can I check if my venue data is complete using IndoorAtlas (Indoor Positioning) MCP Server? +
Yes. Run get_venue_details to get metadata like floor count and total mapped area. You can also check coverage by running get_fingerprint_paths.
How do I find all the available floor plans for a specific building? +
Use list_floorplans. This tool returns IDs and metadata for every floor plan uploaded to the venue, along with their dimensions and map generation status.
How do I use the `position_from_wifi_scan` tool to determine indoor location? +
You provide the raw Wi-Fi signal strengths and the desired coordinates. The tool returns the estimated latitude, longitude, and floor level, along with an accuracy estimate. This is useful when you can't run a mobile SDK.
What information does `get_venue_details` return about a location? +
It returns the venue's core configuration, including its geographic anchor point, total mapped area, floor count, and current calibration status. This lets you inspect the venue before deploying any features.
When should I run `trigger_map_generation` after uploading a floor plan? +
You must run trigger_map_generation after uploading a floor plan with upload_floorplan_geojson. This initiates the server-side computation needed to build the positioning model. Remember, this process takes time.
How can I list all available physical buildings using `list_venues`? +
Simply call list_venues with no arguments. It returns an array of all venues registered in your organization, giving you IDs, names, and geographic coordinates.
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.
Use it with your favorite AI tools
Connect this server to Cursor, Claude, VS Code, and more.
More in this category
Grain Watch
Access silo temperature monitoring via Grain Watch — track grain temperature, humidity, hot spots, and spoilage risk from any AI agent.
Vertiv Environet
Monitor data center environmental sensors, alerts, and thresholds via Vertiv Environet Alert API.
Cartrack
Manage fleet operations via Cartrack — track vehicle locations, monitor fuel, and analyze trip history directly from any AI agent.
You might also like
FeedBlitz
Manage mailing lists, RSS feeds, and email marketing campaigns through AI.
Bitstamp
Trade and monitor crypto markets via Bitstamp — get tickers, order books, account balances, and manage orders.
Meituan Waimai
Essential food delivery gig API — manage orders, track delivery, handle refunds, and control restaurant menus via Meituan Waimai.