Public Preview ChatGPT is OpenAI’s AI assistant, available as a native desktop app for macOS and Windows and a browser-based app. Both support MCP integrations through Apps, allowing you to connect Wherobots tools directly.Documentation Index
Fetch the complete documentation index at: https://docs.wherobots.com/llms.txt
Use this file to discover all available pages before exploring further.
Component Overview
Wherobots’ Agentic Tools consist of the following components that work together to provide our agentic experience:MCP Server
MCP Server
Connects your AI assistant to Wherobots Cloud for catalog exploration, Spatial SQL generation, and query execution.
Agent Skills
Agent Skills
Gives your AI assistant domain-specific Wherobots knowledge for more accurate commands and fewer errors.
Wherobots CLI
Wherobots CLI
Wraps the full Wherobots API into a single binary for job submission, log streaming, and automation.
Why use Wherobots’ agentic tools?
Wherobots’ agentic tools connect your AI assistant to Wherobots Cloud and your local development environment so you can interact with your spatial data, catalogs, and jobs in a more intuitive way.Explore your spatial catalog conversationally
Explore your spatial catalog conversationally
The MCP Server connects your AI assistant to Wherobots Cloud so you can browse catalogs, databases, and table schemas (including Overture Maps and your own datasets) by asking questions in plain language instead of navigating the console.
Generate Spatial SQL without memorizing functions
Generate Spatial SQL without memorizing functions
Describe a geospatial task (e.g. “find buildings within 500m of this point”) and the MCP Server returns optimized Spatial SQL using WherobotsDB’s ST functions, spatial joins, and indexing patterns.
Submit and monitor Wherobots jobs from your editor
Submit and monitor Wherobots jobs from your editor
Use the CLI or the extension to submit Spark job runs, stream logs in real time, check resource metrics, and cancel jobs without leaving your editor or terminal.
Get Wherobots-aware AI assistance
Get Wherobots-aware AI assistance
Agent Skills teach your AI assistant Wherobots-specific APIs, query patterns, and workflow sequences so it produces correct
wherobots CLI commands, valid MCP tool calls, and accurate notebook code on the first try.Before you start
The following prerequisites are required:- A ChatGPT account with an active paid plan (Plus, Pro, Business, or Enterprise).
- A Wherobots Account within a Professional or Enterprise Organization. See Create a Wherobots Account.
- For the desktop flow: ChatGPT Desktop installed.
Install and configure
In ChatGPT, custom MCP servers are added as Apps. Each user creates the Wherobots App on their own account. The same steps work in ChatGPT on the web and ChatGPT Desktop.Open the Apps settings
- In ChatGPT, go to Settings > Apps > Advanced settings.
-
Enable Developer mode.
This allows you to add custom MCP servers as Apps in ChatGPT.

- Go back to Settings > Apps.
-
Click Create app.

Configure the Wherobots app
In the New App form, enter:
- Name:
wherobotsor a name of your choice (e.g.Wherobots Geospatial Assistant) - Description (optional): a short description, such as
AI-assisted geospatial development with Wherobots - MCP Server URL:
https://api.cloud.wherobots.com/mcp/ - Authentication:
OAuth

Complete the OAuth flow
- A new browser tab opens to the Wherobots sign-in page.
-
Sign in to Wherobots, select your Organization from the Organization access dropdown, and click Allow access.

-
Return to ChatGPT, go to Apps.
Wherobots now appears under your Enabled apps with the
DEVbadge.
Verify installation
Ask a question in ChatGPT:list_catalogs) and return the catalogs available in your Organization.
Next steps
MCP Server Best Practices
Common tasks, example prompts, and cost considerations for the MCP Server.
MCP Server Demo Videos
Watch the MCP Server automate catalog discovery, spatial queries, and notebook generation.
Agent Skills
Learn more about available skills and installation options.
MCP Server vs CLI
Understand when to use the MCP Server vs. the CLI.


