Skip to main content
Wherobots provides agentic components that bring AI-assisted geospatial development to your editor or terminal. What you need to install depends on your tool. Pick yours below to get started.

​
Pick your tool

Wherobots works in Code OSS-based editors and in AI assistants that support MCP.

Editors

VS Code, Cursor, Kiro, Windsurf, Positron, Antigravity, Trae, and VS Codium. Install the Wherobots VS Code Extension. In VS Code, it also sets up the MCP Server and Agent Skills.

AI assistants

Claude Code, Codex, OpenCode, Claude, and ChatGPT. Connect the Wherobots MCP Server. Terminal agents can also add Agent Skills and the CLI.
Using a Code OSS editor not listed here? Follow Other Code OSS editors and substitute your editor’s CLI command. The extension is available from the Open VSX Registry.

​
What each component does

The Wherobots VS Code Extension turns Code OSS editors into a geospatial workspace with notebook development, job submission, data browsing, and workspace management. In VS Code, it also automatically configures the MCP Server and includes Agent Skills. Wherobots also provides these components:
Connects your AI assistant to Wherobots Cloud for catalog exploration, documentation search, read-only Spatial SQL queries, and workload and Spark execution details.
Gives your AI assistant domain-specific Wherobots knowledge for more accurate commands and fewer errors.
Wraps the full Wherobots API into a single binary for job submission, log streaming, and automation.

​
What you can do with them

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.
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.
Describe a geospatial task (e.g. “find buildings within 500m of this point”) and your AI assistant writes Spatial SQL with WherobotsDB’s ST functions, using the table schemas and documentation that the MCP Server provides, then runs it on Wherobots Cloud.
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.
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.

​
MCP Server or CLI

The MCP Server and the Wherobots CLI are complementary. The MCP Server is designed for query generation, conversational data exploration, and read-only inspection of your workloads. The CLI is designed for interactive and agent-driven job management: running jobs, monitoring workloads, and calling the Wherobots API from your terminal. The MCP Server reads workloads and their logs; to submit or cancel job runs from your terminal, use the CLI. Commands and their underlying APIs may change between CLI releases, so don’t take a dependency on the CLI for recurring production pipelines. For pipelines, use the Runs REST API or the Wherobots Apache Airflow Provider.

​
Setup by tool

Every supported tool connects to the same Wherobots MCP Server. Editors and terminals also get AI-assisted job submission through the Wherobots extension or CLI. The ChatGPT and Claude connectors run in a chat app, so their Wherobots setup covers the MCP Server only, with no extension, CLI, or Agent Skills install. How the MCP Server and Agent Skills are installed also differs: the Wherobots extension configures them automatically in VS Code, while other tools require a one-time manual setup. Here’s what you’ll set up for each tool:
  • Included: configured for you when the extension installs.
  • Additional Setup Required: you install or configure it yourself. See Editors or AI assistants.
  • N/A: Not part of the tool’s Wherobots setup (e.g. no extension for terminal-only tools or chat apps).