# Arcgis Cupertino [Health: Active]

**Category:** 🗺️ Location Services  
**Repository:** https://github.com/pipeworx-io/mcp-arcgis-cupertino  
**GitHub Stars:** 0  
**npm Downloads (last month):** 462  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/arcgis-cupertino

## Description
City of Cupertino GIS — Cupertino, California open geospatial data (ArcGIS).

## Tools
Capabilities this server exposes over MCP:

- **search_datasets** — Search City of Cupertino GIS open geospatial datasets (parcels, zoning, public works & city services) by keyword. Returns each dataset's name, summary, record_count, owner/org, and its Feature Service `url` — pass that url to query_layer / layer_info.
- **query_layer** — Query an ArcGIS Feature Service / Map Service layer by its url (from search_datasets). SQL-like `where`, comma-separated `out_fields`, `order_by`, `limit`, `offset`. Returns attribute rows (and geometry). Use where="1=1" + out_fields="*" to sample.
- **layer_info** — Get an ArcGIS Feature/Map Service layer's schema by url: fields (name + type), geometry type, total record count, and capabilities.

## Claude Desktop Quick Installation
Install path detected from listing signals. Uses `npx` (confidence: high):

```json
"mcpServers": {
  "arcgis-cupertino": {
    "command": "npx",
    "args": ["-y","@pipeworx/mcp-arcgis-cupertino"]
  }
}
```

## Documentation

## What Arcgis Cupertino MCP server does

Arcgis Cupertino MCP server connects MCP-compatible agents to City of Cupertino’s open geospatial data published through ArcGIS. The available datasets include areas such as parcels, zoning, public works, and city services. Results can include dataset names, summaries, record counts, owning organizations, service URLs, attribute rows, and geometry.

This fits the Location Services category for workflows that need municipal GIS data rather than general geocoding or mapping. It is useful when an agent must first find a relevant dataset, understand its schema, and then retrieve matching records.

## How it works

The normal workflow starts with `search_datasets`, using a keyword to find relevant Cupertino GIS datasets. Each result provides a Feature Service URL that can be supplied to the other tools.

`layer_info` examines a Feature Service or Map Service layer before querying it. It returns field names and types, geometry type, total record count, and declared capabilities. `query_layer` then accepts the layer URL and supports a SQL-like `where` expression, comma-separated `out_fields`, `order_by`, `limit`, and `offset`. Returned records contain attributes and may include geometry. To sample a layer, use `where="1=1"` with `out_fields="*"`.

The hosted endpoint also exposes shared Pipeworx gateway tools in addition to this pack’s three listed tools. Those shared tools can route questions across the broader catalog. The local package exposes only the Arcgis Cupertino tools.

## Setup and configuration

For a remote connection, add the streamable HTTP endpoint `https://gateway.pipeworx.io/arcgis-cupertino/mcp` to an MCP client. The full Pipeworx endpoint, `https://gateway.pipeworx.io/mcp`, is another option when an agent should access all available packs directly.

A local installation is available through the npm package `@pipeworx/mcp-arcgis-cupertino`. Configure the client to run `npx -y @pipeworx/mcp-arcgis-cupertino`; the process communicates over standard input and output. The local mode does not require a Pipeworx account or gateway round-trip.

## Tools and capabilities

Arcgis Cupertino MCP server provides:

- `search_datasets` for keyword searches across Cupertino GIS datasets.
- `query_layer` for filtered and paginated records from ArcGIS Feature Service or Map Service layers.
- `layer_info` for schemas, geometry details, record totals, and capabilities.
- Attribute and geometry retrieval from matching layer records.
- Direct HTTP tool calls for clients that do not support MCP, using the gateway’s `/v1/tools/` endpoints.

The pack is an independent, unofficial integration and is not affiliated with, endorsed by, or published by the upstream provider.

_Full upstream README: https://allmcps.com/mcp/arcgis-cupertino/readme_