Data Delaware logo

Data Delaware

Query Delaware’s Socrata open-data catalog, inspect dataset schemas, and retrieve rows with SoQL through MCP.

Install Data Delaware

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

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-delaware

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 4d ago.

Overview

The Data Delaware MCP server connects AI clients to Delaware Open Data at data.delaware.gov through Socrata APIs. It provides tools to find datasets, inspect metadata, and run SoQL queries with filters, projections, grouping, sorting, limits, and offsets. Use it when an agent needs current Delaware public data in structured JSON. It is available as a hosted MCP endpoint through Pipeworx or as a local stdio package.

Use cases

  • Find Delaware public datasets by topic
  • Inspect columns and update details before querying
  • Run filtered SoQL queries against Delaware data
  • Retrieve paginated JSON rows for analysis

Key features

  • Keyword search across the Delaware Open Data catalog
  • Dataset schema and metadata inspection
  • Socrata SoQL querying
  • Filtering, grouping, sorting, and pagination
  • Hosted HTTP and local stdio access

Tools3

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

Self-reported~142 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 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 15d ago via OSV.dev · @pipeworx/mcp-data-delaware (npm)

Adoption & maintenance

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

Last commit28d agoMost recent push to the default branch.
Install checkInconclusiveStarted but did not complete the MCP handshake in our test.
Tools exposed3Callable tools this server registers over MCP.
Directory activity1 viewsConfig copies, upvotes, and views on AllMCPs.

How Data Delaware works

What the Data Delaware MCP server does

The Data Delaware MCP server exposes Delaware’s public Socrata catalog to MCP-compatible AI clients. It focuses on three operations: finding relevant datasets, examining a dataset’s structure, and retrieving rows from a selected dataset. Results from queries are returned as JSON, making the server suitable for agents that need to inspect or analyze structured public records.

The hosted endpoint is part of Pipeworx. A direct connection exposes the Delaware-specific tools along with shared Pipeworx gateway tools. The local package exposes only the Delaware tools and does not include the gateway’s shared routing or memory-related tools.

How it works

Start with datasets when the dataset identifier is unknown. The tool searches the Delaware Open Data catalog by keyword and returns each match’s resource_id, name, description, category, and update date. Pass the returned identifier to the other tools.

Use metadata to inspect a dataset before querying it. The response includes columns, data types, row count, category, and last-updated information. Use query to execute a Socrata SoQL request against the selected resource. Its arguments support where, select, group, and order clauses without the leading dollar sign, plus limit and offset. Matching rows are returned as JSON.

The hosted MCP connection uses https://gateway.pipeworx.io/data-delaware/mcp. Pipeworx also offers a full gateway endpoint at https://gateway.pipeworx.io/mcp; either endpoint can reach the broader Pipeworx catalog through the shared ask_pipeworx tool, while the pack endpoint lists the Delaware tools directly.

Setup and configuration

For Claude Desktop, Cursor, Windsurf, or another MCP client that accepts remote endpoints, add the hosted URL as an MCP server.

For local use, run the package with npx -y @pipeworx/mcp-data-delaware and configure the client to launch that command. The local process communicates over standard input and output, requires no Pipeworx account, and avoids a gateway round trip. It responds to MCP initialize, tools/list, and tools/call requests.

The tools can also be called over HTTP without an MCP client. Pipeworx documents endpoints under https://gateway.pipeworx.io/v1/tools/, including data_delaware_datasets for catalog searches.

Tools and capabilities

  • Search Delaware datasets by keyword.
  • Retrieve dataset schemas and descriptive metadata.
  • Run SoQL queries against a dataset resource.
  • Filter, select, group, order, limit, and paginate query results.
  • Return query rows as JSON.

Limitations and notes

It does not provide a general database connection or claim access to datasets outside that source.

The hosted pack endpoint includes shared Pipeworx meta-tools in addition to the three Delaware tools, so its tool listing is larger than the pack’s core tool list. The local stdio mode does not include those shared tools. The gateway’s exact tool scope can change; its initialize response is authoritative for a particular connection.

The project is licensed under MIT.

Reviews

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

Frequently Asked Questions about Data Delaware

Data Delaware is an MCP server that connects AI clients to Delaware Open Data at data.delaware.gov through Socrata. Its main tools search datasets, retrieve dataset metadata and schemas, and run SoQL queries against selected resources, returning catalog details or matching rows as JSON.

Install it locally by configuring your MCP client to run `npx -y @pipeworx/mcp-data-delaware`. This starts the standalone stdio server without a Pipeworx account. You can instead configure the hosted endpoint at `https://gateway.pipeworx.io/data-delaware/mcp`.

First use `datasets` to find a resource ID, then call `metadata` to inspect its schema and `query` to retrieve rows. The query tool accepts SoQL clauses such as `where`, `select`, `group`, and `order`, along with `limit` and `offset`.

Yes, Data Delaware works with Cursor through the hosted MCP endpoint or the local stdio configuration. Add `https://gateway.pipeworx.io/data-delaware/mcp` for the hosted connection, or configure Cursor to launch the package with `npx -y @pipeworx/mcp-data-delaware`.

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