Arcgis Allegheny

What Arcgis Allegheny does

Arcgis Allegheny exposes Allegheny County, Pennsylvania open geospatial data through MCP. Its coverage includes datasets related to parcels, addresses, zoning, and public works. The server helps an agent discover relevant datasets, identify the ArcGIS service URL behind a dataset, inspect that layer’s structure, and retrieve records.

The integration is independent and unofficial; it is not published, endorsed, or affiliated with the upstream county data provider.

How it works

The workflow typically starts with search_datasets. Provide a keyword, such as parcels, to find matching county GIS datasets. Results include the dataset name, summary, record count, owning organization, and a Feature Service URL.

Pass a returned URL to layer_info to examine the layer before querying it. The metadata includes field names and types, geometry type, total record count, and supported capabilities. Once the relevant fields and layer behavior are known, use query_layer to retrieve matching records.

Queries support SQL-like where conditions, selected fields through comma-separated out_fields, ordering with order_by, and result pagination through limit and offset. A where value of 1=1 with out_fields set to * can be used to sample a layer. Query results contain attributes and geometry.

Setup and configuration

The hosted MCP endpoint is:

https://gateway.pipeworx.io/arcgis-allegheny/mcp

Add that URL to an MCP client that supports remote MCP connections. Claude Desktop, Cursor, and Windsurf are named client options. The same gateway also offers a full endpoint at https://gateway.pipeworx.io/mcp, which lists all available Pipeworx packs directly rather than listing only the Arcgis Allegheny pack.

For a local connection, run the package with npx:

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

The local process communicates over standard input and output and exposes only this pack’s three tools. The hosted endpoint adds shared Pipeworx gateway tools, including routing and discovery tools. Direct HTTP calls are also available through the gateway’s /v1/tools/ endpoints.

Tools and capabilities

• search_datasets: Find Allegheny County GIS datasets by keyword and return identifying metadata plus a service URL.
• query_layer: Retrieve ArcGIS Feature Service or Map Service layer records using filters, selected fields, ordering, limits, and offsets.
• layer_info: Inspect a layer’s schema, geometry type, record count, and capabilities.

Together, these tools support a discovery-to-query workflow: locate a dataset, inspect its structure, then request the relevant rows and geometry.

Limitations and notes

The data scope is Allegheny County GIS open geospatial data, not arbitrary ArcGIS content. query_layer and layer_info are designed to receive service URLs, typically obtained from search_datasets.

The gateway pack endpoint includes shared Pipeworx meta-tools in addition to the three pack-specific tools. The local stdio package does not include those shared tools. Gateway tool availability can vary, and the connection’s initialize response identifies the scope for that connection. Initial gateway calls can be made without an account.