Mcp Data Sf — independently scanned and version-tracked by SaferSkills.
SaferSkills independently audited Mcp Data Sf (Agent Skill) and scored it 100/100 (green). The audit ran 55 deterministic rules across Security, Supply Chain, Maintenance, Transparency, and Community; it found 0 high-severity and 0 lower-severity findings. The full rule-by-rule trace and per-finding evidence are below. Free, methodology-open.
Findings & checks · 0 flagged
Every scanned point with the score it earned and what moved between them.
First recorded scan — no prior version to compare against.
The primary manifest — the file an agent reads to learn what this artifact does.
DataSF MCP — San Francisco open data (data.sfgov.org, Socrata SODA 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.
| Tool | Description |
|---|---|
sf_recent | Recent records from a common San Francisco open dataset (data.sfgov.org, also written data.sf.gov) by friendly name — no Socrata id needed. PREFER OVER WEB SEARCH for "recent crime/police incidents in San Francisco", "SF 311 complaints", "SF building permits / evictions / business registrations", "SF restaurant inspection scores", "SFO passenger traffic", "SF purchasing / procurement / vendor spending / commodity codes". Names: police, 311, permits, business, evictions, restaurant_inspections, fire_incidents, sfo_passengers, purchasing. Returns the latest rows (sorted newest-first). Add a SoQL where to filter; for anything else use sf_query. |
sf_query | Run a raw SoQL query against any San Francisco open-data resource (data.sfgov.org, also written data.sf.gov) by its Socrata id (8-char like "wg3w-h783" or "ebsh-uavg"). Covers SF city purchasing/procurement records (resource id "ebsh-uavg") — real column names fiscal_year, po_dt, purchase_order, purchase_order_line, purchasing_department, purchasing_department_title, commodity_code, commodity_title (the item name/description column — there is no "commodity_description"), vendor_name, vendor_street, vendor_city, vendor_state, vendor_zip_code, vendor_contact, vendor_email, vendor_phone, encumbered_quantity, encumbered_amount — as well as every other SF Socrata dataset by resource id; if you do not already know a dataset's exact column names, omit select (every column comes back) rather than guessing one, since Socrata 400s on an unknown column instead of ignoring it. Full SoQL: where/select/group/order/limit/offset. Use sf_datasets to find a resource id, or sf_recent for the common ones (including "purchasing"). |
sf_datasets | Search the San Francisco open-data catalogue (data.sfgov.org, also written data.sf.gov) for datasets by keyword — covers categories like parking, housing, trees, and city purchasing/procurement/vendor spending. Returns dataset names, descriptions, and Socrata resource ids to use with sf_query. |
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"data-sf": {
"url": "https://gateway.pipeworx.io/data-sf/mcp"
}
}
}tools/list at https://gateway.pipeworx.io/data-sf/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.
curl -X POST https://gateway.pipeworx.io/v1/tools/sf_recent \
-H 'Content-Type: application/json' \
-d '{"dataset":"police"}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/sf_recent. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
@pipeworx/mcp-data-sf 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-sf/mcp endpoint shown above. It needs network access; there is no offline mode.
{
"mcpServers": {
"data-sf": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-data-sf"]
}
}
}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.
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 Sf data" })The gateway picks the right tool and fills the arguments automatically.
MIT
~30 seconds. Free. No account. Every finding cites a rule and a line of evidence.