Connect U.S. Bureau of Labor Statistics (BLS) to Codex
Query U.S. Bureau of Labor Statistics (BLS) directly from Codex. Arlet links the two through one MCP connection and takes care of API keys.
This server connects your AI client to the Bureau of Labor Statistics Public Data API - the primary source for the US employment situation and inflation figures that move markets.
Key features:
- get_series: fetch up to 50 series in one call by BLS series ID, over a year range (up to 20 years). Values come back newest first with the 1-period and 12-month percent changes computed by BLS itself, so a question like 'what is the current CPI year-over-year inflation rate' is answered without any client-side math.
- list_popular_series: a curated catalog of the most commonly used IDs (unemployment rate LNS14000000, nonfarm payrolls CES0000000001, CPI-U CUSR0000SA0, PPI final demand WPUFD4, JOLTS job openings, ...) - the BLS API itself has no series search, so this is the entry point.
Division of labor with FRED: FRED mirrors most headline BLS series and is better for cross-source discovery, while this server is the primary source with BLS's own calculations and catalog metadata (survey name, seasonality).
Using the API requires a free registration key from data.bls.gov/registrationEngine. Set it as BLS_API_KEY in your Arlet environment variables. The v2 API allows 500 requests per day per key.
How to connect U.S. Bureau of Labor Statistics (BLS) to Codex
- 1
In the Arlet dashboard, open Data tools, find U.S. Bureau of Labor Statistics (BLS), set the API key issued by U.S. Bureau of Labor Statistics (BLS) and switch it on.
- 2
In your terminal, run codex mcp add arlet --url https://mcp.arlet.dev/mcp/ to add Arlet as an MCP server.
- 3
Codex detects OAuth support and opens your browser. Sign in with Google and click Allow on the consent screen.
- 4
Once connected, both the CLI and the IDE extension can call Arlet tools (the configuration is shared).
If the browser does not open, run codex mcp login arlet to redo the authentication.
