Data Providence logo

Data Providence

Searches Providence Open Data, runs SoQL queries, and retrieves dataset schemas and metadata through MCP.

Install Data Providence

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "data-providence": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-data-providence"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Automated check passed— started and listed 3 tools correctly (6d ago).

Overview

Data Providence MCP server connects AI agents to the Providence Open Data catalog at data.providenceri.gov through Socrata. It provides tools to find datasets, inspect schemas and metadata, and run SoQL queries against selected resources. Use it when an agent needs structured Providence datasets or filtered JSON results without manually navigating the catalog. The service is available through the Pipeworx gateway or as a local stdio package.

Use cases

  • Search Providence datasets by topic
  • Inspect dataset columns before querying
  • Run filtered SoQL queries against city data
  • Paginate through matching Providence records

Key features

  • Keyword search across the Providence Open Data catalog
  • Socrata SoQL query execution
  • Dataset schema and metadata inspection
  • JSON row results
  • Hosted gateway and local stdio deployment

Tools3

What Data Providence lets your agent do. Expand a tool for its parameters.

Verified live~410 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 2d ago

Recent health check succeeded.

7/7 checks healthy over the last 46d

What it can do

From the 3 tools this server returned when we ran it.

Read-only tools · 3
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age113 days
Maintainers1

Observed 2026-10-17 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 15d ago via OSV.dev · @pipeworx/mcp-data-providence (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads442Package downloads in the last 30 days.
Last commit28d agoMost recent push to the default branch.
Availability100%Our rolling endpoint + install checks that succeeded.
Install checkPassedOur sandbox started it and listed its tools.
Tools exposed3Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Data Providence works

What Data Providence MCP server does

The Data Providence MCP server gives MCP-compatible agents access to Providence Open Data at data.providenceri.gov. It focuses on three operations: locating datasets, examining a dataset before querying it, and retrieving rows from a selected dataset.

The catalog search accepts a keyword and returns matching resources with identifying and descriptive fields, including the resource ID, dataset name, description, category, and update date. That resource ID is then used with the other tools. This workflow is useful when an agent knows the subject of the data but not the Socrata identifier.

How it works

The Data Providence MCP server uses Socrata resources exposed by the Providence Open Data site. An agent can search for a resource, request its schema and other metadata, then send a Socrata SoQL query using the resource ID. Query results are returned as JSON rows.

The query tool accepts where, select, group, and order clauses, along with limit and offset. The SoQL clause values should be supplied without the leading $ used in some HTTP examples. A typical sequence is to call datasets, select a returned resource ID, call metadata to inspect available columns, and then call query with the required filters or projections.

Setup and configuration

The hosted MCP endpoint is:

https://gateway.pipeworx.io/data-providence/mcp

An MCP client can register that URL as the data-providence server. The README specifically shows configurations for Claude Desktop, Cursor, and Windsurf. The same gateway also exposes a full Pipeworx endpoint at https://gateway.pipeworx.io/mcp; the scoped endpoint lists this pack directly while also including shared Pipeworx gateway tools.

For a local connection, run the package with npx -y @pipeworx/mcp-data-providence and configure the client to start it as a stdio process. The standalone mode exposes only the three Providence tools and does not include the gateway's shared meta-tools. HTTP callers can also invoke tools through the Pipeworx /v1/tools/ interface.

Tools and capabilities

  • datasets: searches the Providence catalog by keyword and returns resource IDs plus basic dataset details.
  • metadata: returns schema information, column types, row count, category, and last-updated information for a resource ID.
  • query: runs a SoQL query and returns matching rows as JSON, with filtering, selection, grouping, ordering, pagination, and row limits.

The Data Providence MCP server is suited to agents that need current catalog entries or structured answers from Providence datasets. Metadata inspection helps an agent construct queries against the actual columns rather than assuming a schema.

Limitations and notes

The tools operate on Providence Open Data resources and require a valid Socrata resource ID for metadata and query operations.

The hosted pack endpoint includes shared Pipeworx tools in addition to the Providence-specific tools, so its tool list is larger than the three listed here. Its exact scope may change and is reported by the MCP initialize response. The local package avoids those shared tools but also does not provide cross-catalog routing through ask_pipeworx.

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Data Providence

Data Providence is an MCP server that connects AI agents to Providence Open Data at data.providenceri.gov. Its main tools search the dataset catalog, retrieve schema and metadata for a resource, and run Socrata SoQL queries with filtering, grouping, ordering, limits, and offsets, returning matching rows as JSON.

Run it locally with `npx -y @pipeworx/mcp-data-providence` and configure your MCP client to use that command over stdio.

Search for a dataset with `datasets`, use its returned resource ID, and then call `query` with SoQL clauses such as `where`, `select`, `group`, or `order`. You can also provide `limit` and `offset`, and query results are returned as JSON.

Yes. Call `metadata` with the dataset's resource ID to retrieve columns, types, row count, category, and last-updated information. The result can help an agent construct a query using the dataset's actual fields.

Yes. Cursor is named in the README as an MCP client for the hosted endpoint. Add `https://gateway.pipeworx.io/data-providence/mcp` to Cursor's MCP server configuration, or run the standalone package locally over stdio.

Related MCP servers

Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewData Providence AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/data-providence?style=directory)](https://allmcps.com/mcp/data-providence)
HTML Embed
<a href="https://allmcps.com/mcp/data-providence"><img src="https://allmcps.com/api/badge/data-providence?style=directory" alt="Data Providence on AllMCPs" /></a>