Log inSubmit server
Bls logo

Bls

Queries official BLS data for economic series, latest values, local unemployment, and occupation projections.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Bls

Pick your client, then add it in one click or paste the config.

STDIONode.js
~/Library/Application Support/Claude/claude_desktop_config.json
claude_desktop_config.json
{
  "mcpServers": {
    "bls": {
      "command": "npx",
      "args": [
        "-y",
        "@pipeworx/mcp-bls"
      ]
    }
  }
}

Settings → Developer → Edit Config, merge this into mcpServers, then fully quit and reopen Claude Desktop.

Install not yet sandbox-tested— the server itself is confirmed live (we called its tools/list endpoint). The stdio install command is a separate, ongoing check.

Overview

Bls MCP server connects AI agents to the U.S. Bureau of Labor Statistics data API. It searches and retrieves historical series, returns the latest observations, browses common series, and resolves local unemployment by county, metro area, or city name. The server also exposes national occupation projection data, including employment change, openings, wages, and education. Use it for official labor-market, price, productivity, housing, and local economic research.

Use cases

  • Find BLS series for national employment or inflation research
  • Retrieve monthly observations for a selected economic indicator
  • Check the latest unemployment or CPI value
  • Compare local unemployment rates by county or metro area
  • Analyze projected occupation growth and annual openings

Key features

  • BLS series search and historical retrieval
  • Latest-value lookups
  • Curated popular-series browsing
  • Place-name resolution for local unemployment
  • National occupation projections
  • Hosted HTTP and local stdio operation

Tools5

What Bls lets your agent do. Expand a tool for its parameters.

Verified live~802 tokens of context

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked 3d ago

Recent health check succeeded.

8/8 checks healthy over the last 50d

What it can do

From the 5 tools this server returned when we ran it.

Makes network requests · 3Read-only tools · 5
Network at startup3 connections
Files written at startupNone
Install scriptsNone
npm provenanceSigned build
Package age184 days
Maintainers1

Observed 2026-10-17 in an isolated sandbox. A description of reach, not a security audit.

Supply-chain signal

No high-severity advisories surfaced by our automated scan.

Critical 0High 0Medium 0Low 0

Scanned 2d ago via OSV.dev · @pipeworx/mcp-bls (npm)

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

npm downloads429Package downloads in the last 30 days.
Last commit4d agoMost recent push to the default branch.
Tools exposed5Callable tools this server registers over MCP.
Directory activity2 viewsConfig copies, upvotes, and views on AllMCPs.

How Bls works

What Bls does

Bls provides MCP access to public data from the U.S. Bureau of Labor Statistics. Its coverage includes employment, unemployment, wages, prices such as CPI and PPI, productivity, housing-related series, and occupational projections. Data is available across national, state, and metro-level contexts, with local-area unemployment lookups for counties, metropolitan areas, and cities or towns.

The main workflow is to find an appropriate BLS series, retrieve its observations, and interpret the returned dates and values. Agents can search by keyword, browse a curated set of commonly used series, or request a known series ID directly. A separate place-name lookup handles local unemployment without requiring callers to construct LAUS identifiers.

How it works

Bls can run as a local stdio process through the @pipeworx/mcp-bls package, or it can be reached through Pipeworx's hosted MCP endpoints. The standalone process communicates over standard input and output and exposes only the BLS pack's tools. The hosted pack endpoint also lists shared Pipeworx tools, including routing and discovery functions; the full gateway endpoint provides access to those shared capabilities and other data packs.

Historical series responses are ordered newest first and include a count plus the observations returned for the requested range. The latest-value operation is intended for current figures when historical context is unnecessary. BLS release schedules vary: employment data is generally released monthly, CPI and PPI arrive around the middle of the month, metro unemployment follows the reference month by roughly three weeks, and productivity is quarterly.

Setup and configuration

For a hosted connection, configure an MCP client with https://gateway.pipeworx.io/bls/mcp. A full-gateway connection uses https://gateway.pipeworx.io/mcp. For local execution, configure the client to run npx -y @pipeworx/mcp-bls, or start that command directly.

BLS API authentication uses a free API key. Supply it as _apiKey on individual calls. Requests without a key are subject to a lower limit of approximately 25 requests per day per IP, while a key raises the limit to approximately 500 per day. Hosted responses are cached with time-to-live values aligned to BLS release schedules.

Tools and capabilities

  • bls_search finds series IDs and titles using keywords.
  • bls_get_series retrieves dated observations for a series, including employment, inflation, wages, productivity, and housing data.
  • bls_latest returns the most recent value and date for a series.
  • bls_popular_series lists commonly used series by employment, inflation, wages, housing, and productivity category.
  • bls_local_unemployment resolves a county, MSA, or city name to a LAUS series and returns recent, non-seasonally-adjusted monthly data. Ambiguous names can produce candidates, and cities below the reporting threshold may fall back to their county.
  • bls_occupation_projections supports occupation searches, SOC-code lookups, and ranking by measures such as projected growth. Results include the latest national projection period, employment, ten-year change, annual openings, median wage, and typical entry education.

Limitations and notes

Series IDs distinguish between seasonally adjusted and not-seasonally-adjusted data, and related series may differ in frequency, geography, and coverage. LNS and LNU prefixes are useful indicators for adjusted and unadjusted national labor series, respectively, but callers should inspect metadata before comparing or plotting results. Not every series exists for every state or metro area, and smaller metros may have longer delays or more imputed values.

The series search catalog is not a substitute for the local-area lookup: use bls_local_unemployment for place names rather than trying to infer LAUS area codes. Year-over-year inflation calculations may require requesting 13 months of data and computing the change. Occupation projections cover the latest release and do not provide earlier vintages.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Bls

Bls is an MCP server that connects AI agents to the U.S. Bureau of Labor Statistics data API. Its tools search series, retrieve historical observations, return latest values, browse popular series, resolve local unemployment by place name, and query occupation projections. It supports employment, inflation, wages, productivity, housing, and related labor data.

Run `npx -y @pipeworx/mcp-bls` locally or add that command to an MCP client's server configuration. You can also connect to `https://gateway.pipeworx.io/bls/mcp` for the hosted endpoint. The local option uses stdio and does not require a Pipeworx account.

Pass a free BLS API key as `_apiKey` on each call. Requests without a key are limited to roughly 25 per day per IP, while keyed requests receive roughly 500 per day. The key is supplied per request rather than through a documented server environment variable.

Call `bls_local_unemployment` with a place name such as a county, MSA, or city, and optionally provide the state. The tool resolves the place to a LAUS series, returns recent non-seasonally-adjusted monthly data, reports ambiguous matches, and can fall back to the county when a city is below the reporting threshold.

Yes, Bls works with Cursor through the hosted MCP URL or a local stdio configuration. Add `https://gateway.pipeworx.io/bls/mcp` as the server URL, or configure Cursor to run `npx -y @pipeworx/mcp-bls`.

Related MCP servers

All in Data Science Tools All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewBls AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/bls?style=directory)](https://allmcps.com/mcp/bls)
HTML Embed
<a href="https://allmcps.com/mcp/bls"><img src="https://allmcps.com/api/badge/bls?style=directory" alt="Bls on AllMCPs" /></a>