Data Ny logo

Data Ny

Query New York State’s Socrata open-data portal through MCP tools for datasets, records, metadata, and column values.

Install Data Ny

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-ny": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-data-ny"
      ]
    }
  }
}

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

We couldn’t confirm it starts correctly

The install command started, but didn't respond the way we expected when we tried to talk to it.

npx -y @pipeworx/mcp-data-ny

initialize succeeded but no response to tools/list.

This is an experimental automated check and can have false negatives — missing environment variables, a slow cold install, etc. It doesn’t necessarily mean something’s wrong. Last checked 15d ago.

Overview

Data Ny MCP server provides agent access to New York State’s data.ny.gov Socrata portal without an API key. It supports dataset discovery, SoQL queries, resource metadata, and distinct column values through MCP, HTTP, or a local stdio package. Use it when an agent needs structured New York open data by resource ID. The gateway endpoint also exposes shared Pipeworx tools, while the standalone package exposes only the Data Ny tools.

Use cases

  • Search the New York State dataset catalog
  • Query Socrata records with SoQL filters
  • Inspect metadata for a data resource
  • Enumerate distinct values in a column

Key features

  • Dataset catalog search
  • SoQL queries against individual resources
  • Resource metadata lookup
  • Distinct column-value lookup
  • Hosted MCP and local stdio modes
  • Optional plain-language routing through ask_pipeworx

Security & health

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

ActiveLast checked 3d ago

Recent health check succeeded.

7/7 checks healthy over the last 46d

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 14d ago via OSV.dev · @pipeworx/mcp-data-ny (npm)

Adoption & maintenance

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

GitHub stars1Stargazers on the source repository.
npm downloads426Package downloads in the last 30 days.
Last commit28d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Directory activity4 viewsConfig copies, upvotes, and views on AllMCPs.

How Data Ny works

What Data Ny MCP server does

Data Ny connects MCP-compatible agents to data.ny.gov, New York State’s open-data portal. The source uses Socrata’s SODA 2.1 JSON resource endpoints, so queries operate against individual datasets identified by their four-by-four resource IDs, such as xj2p-gjci.

The Data Ny MCP server exposes four pack-specific tools:

  • datasets searches the data catalog and accepts optional query, limit, and offset values.
  • query runs a SoQL query against one resource, with optional filtering, selection, grouping, ordering, pagination, and row limits.
  • metadata returns metadata for a resource.
  • column_data returns distinct values from a selected column.

This combination supports finding a relevant dataset, inspecting its structure, querying records, and checking the values present in a field.

How it works

The hosted connection is available at https://gateway.pipeworx.io/data-ny/mcp. An MCP client can initialize the connection, list tools, and call them through the gateway. The pack endpoint includes the four Data Ny tools plus shared Pipeworx gateway tools such as ask_pipeworx, discover_tools, search_within, and remember/recall. The exact tool scope is reported by the connection’s initialize response and may change.

The gateway’s ask_pipeworx tool can accept a plain-language question and select a tool and arguments automatically. It can route across the broader Pipeworx catalog, not only the New York data pack. A full gateway connection at https://gateway.pipeworx.io/mcp lists all packs directly, while both gateway URLs can reach the wider catalog through routing.

The Data Ny MCP server can also run locally over stdin/stdout. The standalone mode uses the same source and pack tools but does not add the gateway’s shared meta-tools or cross-catalog routing.

Setup and configuration

For a hosted MCP connection, add the pack endpoint to the client configuration:

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

For local stdio operation, run the published package with npx:

config.json
{
  "mcpServers": {
    "data-ny": {
      "command": "npx",
      "args": ["-y", "@pipeworx/mcp-data-ny"]
    }
  }
}

The package can also be started directly with npx -y @pipeworx/mcp-data-ny. For clients or scripts that do not use MCP, the gateway provides HTTP tool endpoints, including POST /v1/tools/data_ny_datasets and GET /v1/tools/data_ny_datasets for inspection.

Tools and capabilities

Use datasets before querying when the resource ID is unknown. Once a resource is identified, metadata helps inspect its definition, while query provides record access using SoQL parameters. column_data is useful for enumerating distinct values in a field before constructing a filter.

The service is keyless: the provided configuration does not require a data.ny.gov API token or an environment variable. Hosted and local modes expose the same underlying New York source, but differ in whether gateway-wide tools are included.

Limitations and notes

Queries target one Socrata resource at a time and require its four-by-four resource ID. The pack endpoint does not contain only four tools; shared gateway schemas are listed alongside them. If that additional tool context is undesirable, the local package exposes only the pack tools, while the full gateway avoids mounting several separate pack endpoints.

Treat the initialize response as authoritative for the hosted connection’s current scope.

Reviews

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

Frequently Asked Questions about Data Ny

Data Ny is an MCP server that connects AI agents to New York State’s data.ny.gov Socrata open-data portal. Its main tools search datasets, run SoQL queries on resources, retrieve metadata, and list distinct values from columns. It can run through the Pipeworx gateway or locally as a stdio package.

Use the hosted MCP URL or run the package locally with npx. Add https://gateway.pipeworx.io/data-ny/mcp as the server URL, or configure the command npx with @pipeworx/mcp-data-ny as its package argument.

Yes, Data Ny can be added to Cursor using the hosted MCP endpoint shown in the README. Configure the server URL as https://gateway.pipeworx.io/data-ny/mcp, or use the local npx stdio configuration.

Call the query tool with a Socrata resource ID and optional SoQL arguments such as where, select, group, order, limit, and offset. Use datasets first if you need to find the resource ID, then use metadata or column_data to inspect it.

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