psa-ph
This server does not currently have a deployable release on Glama. Follow the repository's setup instructions to install and configure it for your MCP client, including any required credentials and local dependencies.
@pipeworx/psa-ph
Philippine Statistics Authority (PSA) MCP: find a published table, read its dimensions, and pull labelled figures (consumer prices, inflation, labour force, population, poverty, national accounts, trade, agriculture, tourism and more). Philippines only. Live call per request, nothing stored.
Part of Pipeworx — an MCP gateway connecting AI agents to 2016+ live data sources. This is an independent, unofficial integration — not affiliated with, endorsed by, or published by the upstream provider.
Tools
psa_ph_search_tables(query, limit?)— find tables by keyword. Returns the native table id, title and last-updated date. Index hits for tables PSA has since removed are dropped and counted.psa_ph_table_info(table_id, dimension?, match?)— dimensions of one table with their valid value codes and labels; passdimension(andmatch) to list every value of one dimension.psa_ph_get_data(table_id, select?)— figures as labelled rows.selectmaps a dimension to a value label or code, an array,"*","first","last"or"last:N". Unselected dimensions are defaulted (time dimensions to the latest value, others to the first, usually the total) and every default is listed inselection_resolvedandnote. Selections above 1,500 cells are refused with the per-dimension sizes. A selection that has no published value says why inempty_reason.
Table ids are the publisher's native ids, e.g. 2M/PI/CPI/2018/0012M4ACP09.px; use them exactly as
returned.
Related MCP server: Statline MCP
Auth
Keyless.
Data sources
Philippine Statistics Authority (PSA), OpenSTAT database of official statistical tables.
Notes and traps
The publisher's search index can list tables that have been removed. They are dropped, with a count in
note, so a hit is a table that exists.Value codes are positional strings ("0", "1", ...). Select by label.
A year dimension is usually followed by a period dimension whose last value is the annual average ("Ave"), so the last value of Period is not the latest month. Defaults are reported, never silent.
data_as_ofis the table's last-updated time as the publisher lists it. Theupdatedfield inside a data response is the time of the query and is not used.The units and base year are written in the table title (e.g. "2018=100"); there is no separate unit field.
Quick Start
Add to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):
{
"mcpServers": {
"psa-ph": {
"url": "https://gateway.pipeworx.io/psa-ph/mcp"
}
}
}What this endpoint actually serves
tools/list at https://gateway.pipeworx.io/psa-ph/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 2016+ 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/psa_ph_search_tables \
-H 'Content-Type: application/json' \
-d '{"query":"consumer price index","limit":5}'No account needed for the first calls. Inspect any tool: GET https://gateway.pipeworx.io/v1/tools/psa_ph_search_tables. Find one: POST https://gateway.pipeworx.io/v1/tools/search_packs with {"query":"..."}.
Run it from npm
@pipeworx/mcp-psa-ph 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/psa-ph/mcp endpoint shown above. It needs network access;
there is no offline mode.
{
"mcpServers": {
"psa-ph": {
"command": "npx",
"args": ["-y", "@pipeworx/mcp-psa-ph"]
}
}
}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 Psa Ph data" })The gateway picks the right tool and fills the arguments automatically.
More
License
MIT
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
This server cannot be deployed
Maintenance
Related MCP Connectors
Macroeconomic and other official data from 170+ publishers, resolved from natural language with provenance.
Search and query 1,500+ OECD statistical datasets via SDMX. Keyless.
Official statistics for AI agents: Eurostat, World Bank, OECD, IMF and WHO data for 150+ countries.
Search ILOSTAT labour indicators, query and compare series, build country profiles, run SQL.
Related MCP Servers
- AlicenseBqualityBmaintenanceEnables AI clients to access official Indonesian statistical data from Badan Pusat Statistik (BPS) through natural language queries. It provides over 20 tools for retrieving demographic, economic, and trade data with support for bilingual responses and fuzzy domain matching.34773 npm7MIT
- AlicenseNot gradedqualityBmaintenanceEnables language models to search and query Statistics Netherlands open data, turning natural-language questions into traceable statistics by discovering tables, resolving codes, and retrieving filtered observations.1MIT
- AlicenseNot gradedqualityCmaintenanceEnables AI agents to search, inspect, and retrieve Irish Central Statistics Office PxStat datasets through MCP tools. Supports catalog search, metadata discovery, full-table reads, and filtered JSON-stat queries.65 npmMIT
- AlicenseAqualityBmaintenanceEnables AI assistants to search Austria's free OGD catalog, inspect dataset dimensions and measures, and fetch coded data as readable labels with total-row flags, filters, and paging. It resolves classification files and caches downloads so statistical tables can be queried directly instead of downloaded and pasted.331 PyPIMIT