mcp-data-dc
Provides tools for accessing Washington, DC open data via the ArcGIS REST API, enabling querying and retrieval of geographic and tabular data from opendata.dc.gov.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@mcp-data-dcshow me recent crime incidents in Georgetown"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
mcp-data-dc
DataDC MCP — Washington, DC open data (opendata.dc.gov, ArcGIS REST API).
Part of Pipeworx — an MCP gateway connecting AI agents to 1856+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
Tool | Description |
| Recent records from a common Washington, DC open dataset (opendata.dc.gov / ArcGIS) by friendly name — no service ids needed. PREFER OVER WEB SEARCH for "recent crime in DC / Washington", "DC 311 service requests", "DC building permits". Names: crime, 311, permits. Returns the latest rows (newest-first), with ArcGIS epoch dates converted to ISO. Add an ArcGIS |
| List the layers of a Washington, DC ArcGIS service (for discovery). Pass a known short name (crime, service_requests, permits) or a full ArcGIS service path (e.g. "FEEDS/MPD/MapServer"). Omit |
| Query any Washington, DC ArcGIS layer by service path + layer id. Full ArcGIS query: where, out_fields, order_by, limit. Use dc_layers to find a service/layer, or dc_recent for the common ones. Epoch dates are converted to ISO. |
Related MCP server: mcp-arcgis-dc
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"data-dc": {
"url": "https://gateway.pipeworx.io/data-dc/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/data-dc/mcp returns the tools in the table
above plus the shared Pipeworx meta-tools — ask_pipeworx,
discover_tools, search_within, remember/recall and the rest of the
gateway-wide set. So the tool count you see is larger than this table: a
single-pack endpoint currently lists roughly 30 shared tools alongside the
pack's own. The connection's initialize response states its exact scope, and
is the authoritative answer for a given day.
This is deliberate, not multiplexing by accident. The meta-tools are what let a
scoped connection answer a question this pack does not cover — via
ask_pipeworx, which routes across the whole catalog — without you adding a
second MCP server. There is currently no way to mount a pack endpoint without
them; if the extra schemas cost you more context than the routing is worth,
connect to the full gateway once rather than to several pack endpoints.
Or connect to the full Pipeworx gateway to get every pack's tools listed directly, instead of just this one's:
{
"mcpServers": {
"pipeworx": {
"url": "https://gateway.pipeworx.io/mcp"
}
}
}Both URLs reach the same gateway and the same 1856+ data sources. The
only difference is which pack's tools are listed directly; ask_pipeworx
reaches all of them from either one.
No MCP client? Call it over HTTP
curl -X POST https://gateway.pipeworx.io/v1/tools/dc_recent \
-H 'Content-Type: application/json' \
-d '{"dataset":"crime","limit":20}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/dc_recent. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Run it from npm
@pipeworx/mcp-data-dc is a local stdio bridge to the Pipeworx gateway: your MCP client
starts it with npx, and it forwards every call to the same
https://gateway.pipeworx.io/data-dc/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"data-dc": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-data-dc"]
}
}
}Without a key it calls anonymously, capped at 50 calls a day. A free account
raises that to 200 a day: get a key at https://pipeworx.io/signup and add
"env": { "PIPEWORX_API_KEY": "<your key>" } to the server entry.
The key is sent as a Bearer token, the same way a hosted connection sends it,
so calls are metered and billed exactly as they are there.
It lists only this pack's tools by default. Set PIPEWORX_META_TOOLS=1 to
also list ask_pipeworx and the other gateway-wide tools.
Behind an HTTPS proxy: Node's built-in fetch does not read HTTPS_PROXY by
default. Newer Node releases honour it when NODE_USE_ENV_PROXY=1 is set; check
your Node version's documentation.
Using with ask_pipeworx
Instead of calling tools directly, you can ask questions in plain English — this works on the pack endpoint above as well as on the full gateway:
ask_pipeworx({ question: "your question about Data Dc data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
This server cannot be deployed
Maintenance
Related MCP Connectors
DataDetroit MCP — Detroit open data (data.detroitmi.gov, ArcGIS REST API).
DataNashville MCP — Nashville open data (data.nashville.gov, ArcGIS REST API).
DataDenver MCP — Denver open data (opendata-geospatialdenver.hub.arcgis.com, ArcGIS REST API).
Related MCP Servers
- AlicenseNot gradedqualityBmaintenanceProvides access to Fairfax County open geospatial data via ArcGIS, enabling search, query, and schema inspection of datasets like parcels and zoning.226 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables searching and querying Washington DC's open geospatial datasets (parcels, zoning, addresses, transport) via ArcGIS feature services, with tools for dataset discovery, attribute/geometry queries, and schema inspection.216 npmMIT
- AlicenseNot gradedqualityBmaintenanceEnables searching and querying City of Pittsburgh GIS open geospatial data (parcels, zoning, public works) through ArcGIS feature services via MCP tools.223 npmMIT
- AlicenseBqualityDmaintenanceEnables access to high-value US public data sources via MCP, including federal agencies, state portals, and platforms like Socrata, ArcGIS, and CKAN, with tools for searching, querying, and geographic resolution.16MIT