Bls Labor Mcp Server
by cyanheadscommunityv0.4.6
1
1
An MCP server for querying U.S. Bureau of Labor Statistics data, including survey discovery, series search, historical series retrieval, and latest values. It can also register large result sets as DuckDB-backed dataframes for SQL analysis via additional tools.
From the registry: Fetch US Bureau of Labor Statistics data — CPI, unemployment, wages, JOLTS, and more via MCP.
Install & configure
Prerequisites
- requiredInstall Node.js or BunRequired runtime. The README states Bun v1.3.2+ or Node.js v24+ is needed. For the preferred npx install path, Node.js is sufficient.https://bun.sh/
- optionalOptional BLS API keyA free BLS API v2 key increases quota from 25 requests/day to 500 requests/day. The server can run without it.https://www.bls.gov/developers/home.htm
Install in your client
Paste into the AI you're chatting with — it will figure out the rest
Please install the `bls-labor-mcp-server` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **Install Node.js or Bun** — Required runtime. The README states Bun v1.3.2+ or Node.js v24+ is needed. For the preferred npx install path, Node.js is sufficient. (https://bun.sh/)
Optional prerequisites:
- Optional BLS API key — A free BLS API v2 key increases quota from 25 requests/day to 500 requests/day. The server can run without it. (https://www.bls.gov/developers/home.htm)
Canonical MCP server config (stdio transport):
- command: `npx`
- args: ["-y","@cyanheads/bls-labor-mcp-server@latest"]
- required environment variables:
- `MCP_TRANSPORT_TYPE`: Transport mode for the server. Use stdio for MCP client config. (example: `stdio`)
- optional environment variables:
- `MCP_LOG_LEVEL`: Log level. (example: `info`)
- `BLS_API_KEY`: BLS API v2 key. Optional, but recommended for higher daily quota. (example: `<your-api-key>`)
- `BLS_BASE_URL`: Override the BLS API v2 base URL. (example: `<your-bls-api-base-url>`)
- `BLS_CATALOG_BASE_URL`: Override the LABSTAT flat-file base URL, for example to use a local mirror. (example: `<your-bls-catalog-base-url>`)
- `BLS_DATASET_TTL_SECONDS`: Per-dataframe TTL for canvas-registered tables, in seconds. (example: `<your-ttl-seconds>`)
- `BLS_DATAFRAME_DROP_ENABLED`: Enable the bls_dataframe_drop tool. (example: `<true-or-false>`)
- `CANVAS_PROVIDER_TYPE`: Set to duckdb to enable DataCanvas tabular spillover and dataframe SQL tools. (example: `duckdb`)
- `MCP_AUTH_MODE`: Authentication mode: none, jwt, or oauth. (example: `<none-or-jwt-or-oauth>`)
- `MCP_HTTP_PORT`: HTTP server port when running in HTTP mode; not needed for stdio clients. (example: `<your-port>`)
- `LOGS_DIR`: Directory for log files (Node.js only). (example: `<your-logs-directory>`)
- `OTEL_ENABLED`: Enable OpenTelemetry instrumentation. (example: `<true-or-false>`)
Note: README also documents Streamable HTTP support and a public hosted server at <https://bls-labor.caseyjhand.com/mcp>, but the simplest portable client config shown is stdio via npx. HTTP local startup is described as MCP_TRANSPORT_TYPE=http with MCP_HTTP_PORT set, and the server listens at /mcp.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.Note: README also documents Streamable HTTP support and a public hosted server at <https://bls-labor.caseyjhand.com/mcp>, but the simplest portable client config shown is stdio via npx. HTTP local startup is described as MCP_TRANSPORT_TYPE=http with MCP_HTTP_PORT set, and the server listens at /mcp.
Tools (7)
bls_list_surveys
List BLS survey programs and their metadata, including codes, descriptions, and calculation-support flags.
bls_search_series
Search the BLS series catalog by free text, survey, area, or keywords to resolve SeriesIDs.
bls_get_series
Fetch historical time-series data for 1–50 BLS series, with optional year range and calculations.
bls_get_latest
Return the most recent observation for one or more BLS series.
bls_dataframe_describe
List or inspect dataframes registered by bls_get_series, including provenance, TTL, row count, and schema.
bls_dataframe_query
Run read-only SQL queries against canvas dataframes registered by bls_get_series.
bls_dataframe_drop
Drop a canvas dataframe by name when dataframe dropping is enabled.
Environment variables
BLS_API_KEYBLS v2 API key used to increase daily quota from 25 to 500 requests.Prerequisites
- • Node.js v24+
Packages
@cyanheads/bls-labor-mcp-server
npmv0.4.6transport: stdio
@cyanheads/bls-labor-mcp-server
npmv0.4.6transport: streamable-http
Remote Endpoints
https://bls-labor.caseyjhand.com/mcp
type: streamable-http
Details
- Language
- TypeScript
- License
- NOASSERTION
- Released
- Jun 20, 2026
- Last commit
- Jun 20, 2026
- Registry name
- io.github.cyanheads/bls-labor-mcp-server
Categories
Related Servers
Labelhead Artist Momentum
Trending hip-hop artist momentum scores across four cultural dimensions.
78.5k
PostHog MCP Server
Official PostHog MCP Server for product analytics, feature flags, experiments, and more.
37.7k
Openmetadata Mcp
Official OpenMetadata MCP: governed context and business semantics for AI assistants and agents.
14.9k