About Singstat Sg
Singstat Sg is an MCP server for finding Singapore official statistics tables and retrieving time-series data. It supports keyword search, period filtering, and table metadata lookup, with gateway and local stdio operation.
Key features
- 01Search statistics tables by keyword
- 02Fetch table time-series data
- 03Inspect themes, frequency, and variables
- 04Filter periods and paginate results
- 05Run via gateway or local stdio
Use cases
- 01Find population or employment tables
- 02Retrieve indicators for selected years
- 03Check a table's coverage and variables
MCP support
It exposes tools to MCP clients for searching tables, retrieving data, and inspecting metadata from Singapore's Department of Statistics. It can connect through the Pipeworx gateway or run as a local stdio MCP server.
Configuration
Remote servers need no local install. Pick your client, then copy the config or install in one click.
https://gateway.pipeworx.io/singstat-sg/mcpclaude mcp add --transport http pipeworx-io-singstat-sg https://gateway.pipeworx.io/singstat-sg/mcp{"mcpServers":{"pipeworx-io-singstat-sg":{"type":"http","url":"https://gateway.pipeworx.io/singstat-sg/mcp"}}}Open in Cursor{"servers":{"pipeworx-io-singstat-sg":{"type":"http","url":"https://gateway.pipeworx.io/singstat-sg/mcp"}}}Open in VS Code{"mcpServers":{"pipeworx-io-singstat-sg":{"type":"http","url":"https://gateway.pipeworx.io/singstat-sg/mcp"}}}{"mcpServers":{"pipeworx-io-singstat-sg":{"serverUrl":"https://gateway.pipeworx.io/singstat-sg/mcp"}}}Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.
Tools
Details
From the project READMEmcp-singstat-sg
SingStat Table Builder MCP — Department of Statistics Singapore.
Part of Pipeworx — an MCP gateway connecting AI agents to 1689+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
| Tool | Description |
|---|---|
search_tables | Search Singapore official statistics tables (Department of Statistics Singapore) by keyword. Returns resource ids and titles. The id of a result (e.g. "M810001") is the resourceId used by table_data and table_metadata. |
table_data | Fetch the time-series data rows for a Singapore statistics table. Pass resourceId ONLY if you already have a real one from a prior search_tables/table_metadata call. Otherwise pass search with the topic in plain words (e.g. "resident unemployment rate", "gdp by industry") and this tool resolves the best-matching table itself — the response carries a resolved field naming exactly which table id and title were used, so NEVER guess or reuse an id you saw in an example; it is almost certainly for a different table. Data is returned under Data with a row array of series, each containing dated columns. Filter time periods with timeFilter (comma-separated periods like "2020,2021") or between (a from,to range like "2010,2020"); page with offset/limit. |
table_metadata | Get the structure/metadata for a Singapore statistics table by resourceId (get ids from search_tables): theme, subject, frequency, period coverage and the list of variables/series. Result is under Data.records. |
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"singstat-sg": {
"url": "https://gateway.pipeworx.io/singstat-sg/mcp"
}
}
}
What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/singstat-sg/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 1689+ 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/singstat_sg_search_tables \
-H 'Content-Type: application/json' \
-d '{"keyword":"population"}'
No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/singstat_sg_search_tables. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Standalone (no gateway account)
This package also runs as a local stdio MCP server — no Pipeworx account, no gateway round-trip:
{
"mcpServers": {
"singstat-sg": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-singstat-sg"]
}
}
}
Or run it directly to confirm it starts:
npx -y @pipeworx/mcp-singstat-sg
It speaks MCP over stdin/stdout and answers initialize/tools/list/tools/call
for only this pack's tools — none of the shared meta-tools the gateway
connection above adds. Same source, same tools, no ask_pipeworx routing.
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 Singstat Sg data" })
The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Comments
New to MCP?
From what the protocol is to installing your first server, these answers cover most first questions.
An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.