# Data Pa [Health: Active]

**Category:** 📊 Data Platforms  
**Repository:** https://github.com/pipeworx-io/mcp-data-pa  
**GitHub Stars:** 0  
**npm Downloads (last month):** 442  
**Views:** 1  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/data-pa

## Description
Pennsylvania Open Data (data.pa.gov) Socrata MCP.

## Tools
Capabilities this server exposes over MCP:

- **datasets** — Search the Pennsylvania Open Data catalog of open datasets by keyword. Returns each dataset's resource_id, name, description, category and update date — pass the resource_id to query/metadata.
- **query** — Run a Socrata SoQL query against a Pennsylvania Open Data dataset by resource_id (e.g. "mcba-yywm"). Filter with where/select/group/order (SoQL clauses, without the leading $) plus limit/offset. Returns matching rows as JSON.
- **metadata** — Get a Pennsylvania Open Data dataset's schema + metadata (columns, types, row count, category, last-updated) by resource_id, e.g. "mcba-yywm".

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

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

## Documentation

## What the Data Pa MCP server does

The Data Pa MCP server gives an MCP client access to datasets published in Pennsylvania's Open Data catalog at data.pa.gov. It supports a discovery-to-query workflow: search the catalog, identify a dataset resource ID, inspect its structure, and then retrieve matching records.

Search results include each dataset's resource ID, name, description, category, and update date. The resource ID is the identifier used by the other tools. Metadata requests provide the dataset schema, column types, row count, category, and last-updated information, which helps an agent construct queries against unfamiliar datasets.

## How it works

The Data Pa MCP server exposes three pack-specific tools: `datasets`, `metadata`, and `query`. The `datasets` tool searches the catalog by keyword. The `metadata` tool examines a selected resource, while `query` sends a Socrata SoQL request to that resource and returns matching rows as JSON.

Queries can include `where`, `select`, `group`, and `order` clauses, along with `limit` and `offset` values. The SoQL clause arguments do not include the leading `$`. A typical workflow is to search for a subject such as budgets, use the returned resource ID to inspect columns, and then write a query using the confirmed field names.

The hosted endpoint is `https://gateway.pipeworx.io/data-pa/mcp`. It is a scoped Pipeworx connection, so its tool list also includes shared gateway meta-tools. The gateway can route broader questions through `ask_pipeworx`, and the full gateway is available at `https://gateway.pipeworx.io/mcp` when direct access to all packs is preferred.

## Setup and configuration

Add the hosted endpoint to an MCP client as a server URL. The README specifically lists Claude Desktop, Cursor, and Windsurf as compatible clients. No account is required for the first hosted calls according to the project documentation.

For a local connection, run the package with `npx -y @pipeworx/mcp-data-pa` and configure the client to start that command. This standalone mode communicates over standard input and output, does not require a Pipeworx account, and exposes only the three Data Pa tools rather than the gateway's shared meta-tools.

The tools can also be called over HTTP. For example, the hosted REST-style endpoint for dataset search is `POST https://gateway.pipeworx.io/v1/tools/data_pa_datasets` with a JSON body such as `{"query":"budget"}` and a `Content-Type: application/json` header.

## Tools and capabilities

- `datasets`: Search Pennsylvania's open-data catalog by keyword and return resource IDs plus basic dataset details.
- `metadata`: Retrieve columns, types, row count, category, and last-updated information for a resource ID.
- `query`: Run a SoQL query with selection, filtering, grouping, ordering, limits, and offsets, returning rows as JSON.
- Hosted gateway access: Use shared Pipeworx tools, including `ask_pipeworx`, in addition to the pack-specific tools.

## Limitations and notes

The local package and hosted pack endpoint expose the same Data Pa source tools, but they do not expose the same surrounding tool set. The hosted endpoint includes shared Pipeworx meta-tools, while the local stdio process does not. The gateway's `initialize` response is the authoritative source for the exact hosted tool scope at a given time.

Queries depend on the dataset's current schema and resource ID. Use `metadata` before writing a complex query when column names or types are unknown. The documented license is MIT.

_Full upstream README: https://allmcps.com/mcp/data-pa/readme_