The Wherobots Spatial AI Assistant is now in the Anthropic Connectors Directory

You can now ask Claude questions about the physical world and get answers grounded in real spatial data. 

• Which facilities sit in the path of today’s storms?
• Which county west of the Mississippi has the fewest pharmacies per person?
• How much of Austin’s rooftop area sits under canopy?

The Wherobots Spatial AI Assistant, now available in the Anthropic Connectors Directory, answers these questions in plain language and returns results, maps, and reports directly in your Claude conversation.

Wherobots is the context engine for physical world data. It gives AI the spatial intelligence it needs to reason about where things are, how they relate, and what has happened on the ground. 

Here is an example of an insurance risk analysis of all of Colorado that we initially built with Claude Opus 5 and the Spatial AI Assistant, then expanded on with the VSCode Spatial AI Coding Assistant to be a complete hosted application.

The challenge with traditional data systems for building an application like this is both the skills and the data processing cost. We were able to easily join Regrid parcels with Overtures buildings, build hexes that show various layers of risk derived from open raster data, along with the underlying geometry scored on each parcel in a matter of minutes with a Wherobots large runtime. Having the infrastructure and processing capability at you and your AI’s “fingertips” to build with makes moving from idea to production application far easier and faster than without.

Getting started with the Spatial AI Assistant takes two steps: install the connector, and sign in to your Wherobots organization, and then begin to prompt Claude. With zero additional setup, Claude can begin to utilize datasets including: 

• Overture: Buildings, Transportation, Places
• Foursquare: Open Places 
• NWS Watch/Warnings, updated hourly
• GLO-30/90 DEM Elevation Rasters
• Regrid Parcels (sample) 

See it in action here:

Analyzing open datasets
The Wherobots Global Hub continues to expand the open datasets it offers out of the box. In the near future we plan to add wildfire risk models to the hub in partnership with the USDA Forest Service as well as the national hydrography dataset (NHD). You can also connect to STAC collections for additional raster datasets. If there is open or proprietary data that you are interested in having access to fully supported and maintained by Wherobots while iterating with Claude’s models, reach out to us about it.

Analyzing proprietary datasets
In a few steps, customers can easily attach Wherobots to their S3 storage buckets, catalog systems like Databricks Unity Catalog and AWS Glue Data Catalog, and authoritative 3rd party datasets like Regrid’s Parcels. These integrations enable Wherobots to query proprietary mobility, customer, and asset data with Claude.

Once you’ve connected Wherobots every Claude conversation can query the data Wherobots has access to, so you can test your ideas and drive progress with physical world data.

How the Spatial AI Assistant Works

The Spatial AI Assistant plugs into the Wherobots Spatial SQL API and uses skills for accessing the Wherobots documentation, as well as the datasets registered in the Wherobots Global Hub. Claude uses Wherobots skills packaged with the connector to write strong, valid spatial SQL with (generally) correct functions, syntax, and joins. Results come back into your Claude conversation, ready to work with, and you don’t need to interact with a roadmap or a team of spatial experts to get it. 

Try It Today

There’s a 14 day/$95 free trial available to all first time users to Wherobots that you can utilize to test your ideas. After the trial expires, customers pay a low on-demand rate for Wherobots spatial units consumed through the Spatial SQL API. When you start your trial let us know you have connected the Spatial AI Assistant and you can qualify for an additional $250 in Wherobots credits.

Getting started is easy. Install Wherobots Spatial AI Assistant for Claude, connect your Wherobots organization, and ask your first question like: How much of Austin’s rooftop area sits under canopy?

Want to see what this looks like in practice before you install? Watch the MCP demos in the videos below. The workflows shown there, from natural language questions to working spatial SQL to results on a map, are the same workflows the Spatial AI Assistant puts in front of your entire organization.