{
  "markdown": "# @pipeworx/econdata\n\nUS labor and price statistics from the Bureau of Labor Statistics public API v2 — inflation (CPI-U), the unemployment rate, non-farm payroll employment by industry, and any BLS series by ID.\n\nPart of [Pipeworx](https://pipeworx.io) — an MCP gateway connecting AI agents to 1476+ live data sources.\n\n## Tools\n\n| Tool | What it returns |\n|---|---|\n| `get_cpi` | CPI-U index history for the US city average, all items, with `yoy_inflation_pct` computed per month and a `latest` summary. **Not seasonally adjusted by default** (BLS `CUUR0000SA0`); pass `seasonally_adjusted: true` for `CUSR0000SA0` — the same series FRED publishes as `CPIAUCSL`. Every response names the adjustment it used and carries the other month-matched value as `latest.index_value_sa` / `latest.index_value_nsa`, because the two run about a point apart (2026-07: 333.918 NSA vs 332.813 SA). |\n| `get_unemployment` | Civilian unemployment rate, seasonally adjusted (`LNS14000000`), monthly. |\n| `get_employment_by_industry` | All-employees payroll counts in thousands, seasonally adjusted, for `total_nonfarm`, `manufacturing`, `construction`, `retail`, `financial` or `government`. |\n| `get_series` | Any BLS series by ID, for callers who already know the series they want. |\n\nEvery data point carries an ISO `date` derived from the BLS `period` code (`M01`–`M12` monthly, `Q01`–`Q04` quarterly, `S01`/`S02` semiannual, `A01`/`M13` annual), so results sort and freshness-check without decoding `\"M06\"`.\n\n## Auth\n\nKeyless works, at roughly **25 requests per day per IP**. A free BLS registration key raises that to 500/day: get one at <https://data.bls.gov/registrationEngine/>. The gateway supplies a platform key (`PLATFORM_BLS_KEY`); pass `_apiKey` only to override it with your own.\n\nTwo BLS limits fail differently and the pack distinguishes them, because they used to read alike:\n\n- **Per-second burst** — BLS returns HTTP 429 \"Requests Per Second Limit Exceeded\" when concurrent callers land in the same second. The pack retries three times (400 ms, 1200 ms, 2500 ms); only a 429 that survives all three surfaces, as `upstream_throttled`, saying explicitly that this is *not* the daily quota and *not* an exhausted key.\n- **Daily threshold** — arrives as a `REQUEST_NOT_PROCESSED` body, not an HTTP error. Also surfaced as `upstream_throttled`, with the registration link.\n\n## Data sources\n\n- BLS Public Data API v2 — <https://api.bls.gov/publicAPI/v2/timeseries/data/> (docs: <https://www.bls.gov/developers/api_signature_v2.htm>)\n- Series used: `CUUR0000SA0` / `CUSR0000SA0` (CPI-U, NSA / SA), `LNS14000000` (unemployment rate), `CES*` (Current Employment Statistics by industry)\n\n## Quick Start\n\nAdd to your MCP client (Claude Desktop, Cursor, Windsurf, etc.):\n\n```json\n{\n  \"mcpServers\": {\n    \"econdata\": {\n      \"url\": \"https://gateway.pipeworx.io/econdata/mcp\"\n    }\n  }\n}\n```\n\n### What this endpoint actually serves\n\n`tools/list` at `https://gateway.pipeworx.io/econdata/mcp` returns the tools in the table\nabove **plus the shared Pipeworx meta-tools** — `ask_pipeworx`,\n`discover_tools`, `search_within`, `remember`/`recall` and the rest of the\ngateway-wide set. So the tool count you see is larger than this table: a\nsingle-pack endpoint currently lists roughly 30 shared tools alongside the\npack's own. The connection's `initialize` response states its exact scope, and\nis the authoritative answer for a given day.\n\nThis is deliberate, not multiplexing by accident. The meta-tools are what let a\nscoped connection answer a question this pack does not cover — via\n`ask_pipeworx`, which routes across the whole catalog — without you adding a\nsecond MCP server. There is currently no way to mount a pack endpoint without\nthem; if the extra schemas cost you more context than the routing is worth,\nconnect to the full gateway once rather than to several pack endpoints.\n\nOr connect to the full Pipeworx gateway to get every pack's tools listed\ndirectly, instead of just this one's:\n\n```json\n{\n  \"mcpServers\": {\n    \"pipeworx\": {\n      \"url\": \"https://gateway.pipeworx.io/mcp\"\n    }\n  }\n}\n```\n\nBoth URLs reach the same gateway and the same 1476+ data sources. The\nonly difference is which pack's tools are listed **directly**; `ask_pipeworx`\nreaches all of them from either one.\n\n## Using with ask_pipeworx\n\nInstead of calling tools directly, you can ask questions in plain English —\nthis works on the pack endpoint above as well as on the full gateway:\n\n```\nask_pipeworx({ question: \"your question about Econdata data\" })\n```\n\nThe gateway picks the right tool and fills the arguments automatically.\n\n## More\n\n- [Docs and guides](https://pipeworx.io/docs)\n- [pipeworx.io](https://pipeworx.io)\n\n## License\n\nMIT\n",
  "bytes": 4714,
  "sha": "b59af864ef55239a2942112ae74da82724a1c1eae759f9a6e6510bdfdfc61039",
  "repo_slug": "pipeworx-io/mcp-econdata",
  "fonte": "repo",
  "truncated": false,
  "api": "https://agentalog.com/api/listings/mcp_io_github_pipeworx_io_econdata_1d3124db/readme"
}