# Data Providence [Health: Active]

**Category:** 📊 Data Platforms  
**Repository:** https://github.com/pipeworx-io/mcp-data-providence  
**GitHub Stars:** 0  
**npm Downloads (last month):** 442  
**Views:** 2  
**Installs:** 0  
**Upvotes:** 0  
**Directory Page:** https://allmcps.com/mcp/data-providence

## Description
Providence Open Data (data.providenceri.gov) Socrata MCP.

## Tools
Capabilities this server exposes over MCP:

- **datasets** — Search the Providence 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 Providence Open Data dataset by resource_id (e.g. "vank-fyx9"). Filter with where/select/group/order (SoQL clauses, without the leading $) plus limit/offset. Returns matching rows as JSON.
- **metadata** — Get a Providence Open Data dataset's schema + metadata (columns, types, row count, category, last-updated) by resource_id, e.g. "vank-fyx9".

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

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

## Documentation

## What Data Providence does

Data Providence exposes Providence Open Data as MCP tools. It targets the Socrata catalog at data.providenceri.gov and helps an agent move from dataset discovery to structured data retrieval.

The `datasets` tool searches the catalog by keyword and returns identifiers, names, descriptions, categories, and update dates. Those identifiers can then be supplied to the other tools. The `metadata` tool describes a selected dataset, including its columns, data types, row count, category, and most recent update. The `query` tool executes a Socrata SoQL request and returns matching rows as JSON.

This is a focused option for applications that need Providence-specific public data, such as exploring available datasets or retrieving rows for analysis.

## How it works

A typical workflow starts by calling `datasets` with a keyword. After selecting a returned `resource_id`, an agent can call `metadata` to understand the schema before constructing a query. `query` accepts SoQL clauses through `where`, `select`, `group`, and `order`; these values omit the leading dollar sign used in URL-style SoQL parameters. `limit` and `offset` support bounded and paginated results.

The hosted MCP endpoint is `https://gateway.pipeworx.io/data-providence/mcp`. It lists the three Providence tools along with shared Pipeworx gateway tools such as `ask_pipeworx`, `discover_tools`, `search_within`, and `remember`/`recall`. The hosted connection can therefore route broader questions through `ask_pipeworx`, while the local package exposes only the Providence tools.

The same gateway also offers a full endpoint at `https://gateway.pipeworx.io/mcp`, where tools from all available packs are listed directly.

## Setup and configuration

For a hosted MCP connection, add the following server entry to an MCP client:

```json
{
  "mcpServers": {
    "data-providence": {
      "url": "https://gateway.pipeworx.io/data-providence/mcp"
    }
  }
}
```

The package can also run locally over standard input and output without a Pipeworx account or gateway round trip:

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

To check the local process directly, run `npx -y @pipeworx/mcp-data-providence`. For clients without MCP support, the gateway provides HTTP access through endpoints such as `POST https://gateway.pipeworx.io/v1/tools/data_providence_datasets` with a JSON body like `{"query":"budget"}`. Initial gateway calls do not require an account.

## Tools and capabilities

- `datasets`: searches Providence’s open-data catalog by keyword.
- `metadata`: returns dataset schema and descriptive information.
- `query`: runs SoQL against a dataset selected by `resource_id`.
- SoQL query controls include `where`, `select`, `group`, `order`, `limit`, and `offset`.
- Query results are returned as JSON rows.

## Limitations and notes

The integration is independent and unofficial, and is not affiliated with, endorsed by, or published by the upstream data provider. Hosted connections include shared Pipeworx meta-tools in addition to the pack-specific tools. The local stdio mode does not include those shared tools or cross-catalog routing, but uses the same Providence data tools.

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