Pointr MCP for AI. Map complex indoor paths and locations.
Gemini Works with every AI agent you already use
…and any MCP-compatible client
Connect to your AI in seconds.
Pointr provides access to complex indoor location data for your AI client. This MCP Server lets your agent understand multi-floor building layouts, track physical Bluetooth Low Energy (BLE) beacons, and find specific points of interest (POIs) inside large structures.
You can run pathfinding calculations across multiple levels or audit network coverage by listing all registered hardware.
What your AI can do
Calculate path
Finds the optimal indoor walking path between two given points.
Get building
Retrieves detailed structural configuration for a specific Pointr building ID.
Get level map
Gets the floor plan map data for any specified level within a building.
List all registered buildings and then list the distinct floor levels within a specific building ID.
Determine the optimal path between two points, accounting for structural transitions like escalators or stairs across multiple floors.
List every registered BLE beacon in the system and verify their precise location within the building's map geometry.
Find specific points of interest (POIs) like gates or stores using keywords, even if you don't know the exact POI ID.
Retrieve detailed floor plan data for a given building level to visualize structural constraints and layouts.
List all defined indoor geofences, which are complex polygons used for triggering local alerts.
Ask an AI about this
Waiting for input…
Pointr MCP Server: 10 Tools for Indoor Navigation
Use these tools to list buildings, retrieve floor maps, search points of interest, calculate paths across multiple levels, and audit physical beacon placement.
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 Pointr on VinkiusCalculate Path
Finds the optimal indoor walking path between two given points.
Get Building
Retrieves detailed structural configuration for a specific Pointr building ID.
Get Level Map
Gets the floor plan map data for any specified level within a building.
Get Poi
Retrieves all detailed information about one specific Point of Interest (POI).
List Beacons
Lists every registered BLE beacon and its location within the platform.
List Buildings
Provides a list of all buildings registered in the indoor intelligence system.
List Geofences
Lists every configured internal trigger zone (geofence) for global alerts.
List Levels
Returns all floor levels available inside a specific Pointr building.
List Pois
Lists every registered Points of Interest (POIs) in the entire platform.
Search Pois
Searches for indoor POIs using a simple keyword query.
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.
Claude AI
Open Claude Settings
Go to claude.ai, click your profile icon, then navigate to Customize → Connectors.
Add Custom Connector
Click the "+" button and select Add custom connector. Paste your Vinkius endpoint URL:
https://edge.vinkius.com/[YOUR_TOKEN_HERE]/mcp
Replace [YOUR_TOKEN_HERE] with your token
from cloud.vinkius.com. For OAuth-protected servers, expand
Advanced settings to add credentials.
Start a conversation
Open a new chat. The Pointr integration is available immediately — no restart needed.
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 Pointr, 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 Pointr. 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.
Finding an asset inside a massive building shouldn't require five different dashboards.
Right now, locating anything complex—like a specific gate or junction box in a mall—is a nightmare. You start on the main facility dashboard, click to see floors, then open a separate POI map tool, and if you're lucky, you find the beacon list somewhere else. It’s constant context switching and manual cross-referencing.
With Pointr MCP, your agent handles it all in one flow. You just tell it what you need—say, 'Where is the circuit breaker for Sector 4?' The system uses `list_buildings` to scope the area, runs `search_pois` to find the asset, and gives you its exact location without you clicking a single link.
Pointr MCP Server: Get precise paths and POI details with Pointr.
Before this server, calculating a path from the ground floor to a meeting room on Level 4 required multiple manual steps: get the building ID, find the level IDs (Ground and 4), then feed those into the pathing tool. It was brittle and time-consuming.
Now you just ask your agent for the route between two POIs. The `calculate_path` tool handles the entire journey—the vertical shift via escalator node identification and the horizontal travel on Level 4—in a single, reliable function call.
What your AI can actually do with this
Your AI client uses the list_buildings tool to get a master list of every structure registered with Pointr. From that, it calls list_levels using a specific building ID to map out all the distinct floor levels available in that building.
Once you know the scope—the buildings and the floors—you can use get_building to pull the complete structural configuration data for any single location. This tells your agent exactly what's going on inside, giving it a full model of the environment.
If you need floor plans, calling get_level_map gives you the detailed map data for whatever level you specify. You can also use list_pois to get an exhaustive list of every single Point of Interest (POI) in the entire system. If that list is too long, try search_pois; it lets your agent narrow down POIs using simple keywords—you don't need the ID to find a gate or a store.
The server provides specific details on any given location via get_poi, which pulls all the granular information for one single Point of Interest.
For navigation, you use calculate_path to determine the optimal walking route between two points. This isn't just drawing a line; it calculates paths that account for structural transitions across multiple floors, like stairs or escalators.
To audit what’s actually physically in the building, your agent uses list_beacons to list every registered BLE beacon and pinpoints its exact location on the map geometry. It also manages network alerts by calling list_geofences, which returns all configured internal trigger zones—those complex polygons used for triggering specific local warnings.
The Pointr MCP Server lets your agent understand space itself, treating the building as a structured database of physical reality.
019d75f7-b401-70bd-9cd3-cd56eb4d40be 
Here's how it actually works
The bottom line is: it lets your AI client treat massive indoor maps like simple, navigable code objects.
Append the Pointr connector to your MCP cluster and input your Enterprise Bearer Token.
Instruct your agent to identify the scope of work, perhaps by running list_buildings first.
The agent then sequences calls (e.g., using get_level_map, followed by calculate_path) to analyze the physical location data and deliver a structured result.
Who is this actually for?
Facilities Managers need this when they're stuck clicking through outdated PDFs to find a maintenance panel or spot an offline beacon. Spatial Data Engineers use it when they must extract structured layout data for simulation. Aviation Planners rely on it to model crowd flow before construction starts.
Uses list_beacons and compares the list against active floor geometries to pinpoint hardware that's offline or missing.
Commands the agent to extract large layout configurations using get_level_map, isolating routing constraints directly into code context for analysis.
Runs batch test queries calling calculate_path to simulate customer flow and optimize step logic across a mall or airport area.
What Changes When You Connect
Find the exact path between two points, even if it crosses multiple floors. calculate_path solves for structural transitions like escalators, giving you a continuous route array.
Audit your hardware footprint by running list_beacons. You can check every registered BLE sensor and verify its precise location against the current building geometry to spot gaps.
Understand the full scope of an asset. Use get_building or get_level_map to pull detailed structural data for any specific site, isolating routing constraints into code context.
Quickly locate amenities. Instead of sifting through thousands of records, use search_pois to find a restroom or gate just by typing keywords.
Manage alert zones efficiently. Running list_geofences brings back every complex polygon defined for proactive indoor triggers, letting you audit your entire warning system at once.
See it in action
Finding a missing piece of equipment
A maintenance worker needs to locate a specific junction box in Building X. They run list_buildings first, then use get_building for the ID, followed by list_levels to get floor 2 map data, and finally search_pois with 'junction box' to pinpoint the exact location.
Simulating crowd evacuation flow
A retail planner needs to test an emergency exit route. They call calculate_path, specifying the start POI and end POI, forcing the system to calculate the safest route across multiple floors, ensuring no structural walls are crossed.
Checking beacon coverage after renovations
The facilities team suspects a dead zone. They call list_beacons to see all active hardware and then use get_level_map for the affected floor plan, cross-referencing the list against the map to find gaps.
Auditing multi-zone alerts
The safety team needs to know what areas trigger local alarms. They run list_geofences to pull every active alert polygon, allowing them to verify if all critical zones (like fire exits) are correctly mapped.
The honest tradeoffs
Treating it like simple GPS coordinates
Trying to ask the agent for 'the path from A to B' without specifying floors or POIs, resulting in vague error messages about missing structural context.
Always start by identifying the scope. Use list_buildings and then drill down with get_level_map. Finally, feed those specific coordinates into calculate_path for a reliable route.
Searching only by POI name
Asking to 'find the restroom' when the building has 50 similar rooms. The agent returns too many results without knowing which floor or wing you mean.
Combine tools: first run get_building to narrow down the structure, then use search_pois with keywords AND the correct level ID.
Ignoring beacon deployment status
Assuming that because a POI exists on the map, there's necessarily functioning hardware. The agent reports location data but doesn't know if the sensor is active.
Always run list_beacons alongside your mapping queries. This verifies not just where the point should be, but where the physical network actually resides.
When It Fits, When It Doesn't
Use this Pointr MCP Server if your core problem involves location in a complex, multi-layered structure (e.g., airports, hospitals, massive malls). You need to know about structural boundaries, floor transitions, and physical asset placement. Specifically, you must use it when: 1) You need to calculate movement across floors (calculate_path). 2) You need to audit hardware coverage (list_beacons + get_level_map). 3) Your POIs are complex or require fuzzy searching (search_pois).
Don't use this if you only need basic street-level navigation (use standard mapping services). Don't use it if your location data is simple, single-floor, and doesn't involve beacons. If you just want a list of all known locations without pathing or structural context, list_pois might be enough, but for any operational task, you need the depth this server provides.
Questions you might have
How do I find all registered assets using list_beacons? +
Run list_beacons to get an exhaustive inventory of every beacon. This tool returns the unique ID and the precise location coordinates for each deployed sensor on the platform.
Can I calculate a path across multiple floors using calculate_path? +
Yes, calculate_path is designed to solve multi-story routing. It accounts for structural transitions like escalators and stairs when calculating the optimal sequence of movement.
What if I only know a general area name? Can search_pois help? +
You can use search_pois with keywords (like 'restroom' or 'loading dock'). The tool finds all matching POIs and lets you filter by specific building or level.
Do I need to run get_building first before listing levels? +
Yes. list_levels requires a valid building ID. You should always use get_building or know the target Building UUID first to ensure you're looking at the correct structure.
How do I ensure my credentials are correctly configured when running list_buildings? +
You must provide a valid Enterprise Bearer Token in the configuration vault. This token needs read scope access across all registered Pointr facilities to successfully map and retrieve building data.
What structured format does get_level_map use when retrieving floor plan data? +
It returns geo-JSON polygons defining the precise boundaries of a specific building level. Your agent can parse these coordinates directly to calculate structural constraints and room layouts.
After running search_pois, how do I get comprehensive details using get_poi? +
You must pass the unique POI ID found during your search into get_poi. This call retrieves specific metrics like operational hours, associated geofences, and full physical coordinates.
If I use list_geofences, how does the system handle overlapping logical polygons? +
The platform validates all geometries. If multiple zones overlap, it automatically merges them into a single, comprehensive polygon boundary. This prevents data redundancy and ensures accurate alert triggers.
Can the agent calculate walking paths across multiple floors? +
Yes. When triggering calculate_path supplied with explicit coordinate pairings spanning different Level UUIDs, the Pointr engine bridges the wayfinding automatically. It factors in fixed transitions like elevators or stairs natively, feeding the Agent the comprehensive turn-by-turn array in JSON format seamlessly.
Is it possible to extract the giant raw map shapes for a given floor? +
Absolutely. By initiating the query get_level_map tied securely to a single level UUID, the interface processes and downloads massive explicit geometries mapping out physical walls, traversable space nodes, and internal partitions explicitly generated by the Pointr pipeline.
Can I search for specific stores or bathrooms using text queries? +
Yes. Pointr exposes dense fuzzy logic matching indexes. When the Agent executes search_pois feeding a literal keyword alongside the Target Building ID, it reliably unearths precisely mapped nodes conforming to 'Restroom', 'Exit', or custom store names embedded dynamically.
We've already built the connector for Pointr. 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.
Gemini 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.