BLS MCP
Enables users to query U.S. labor statistics, including employment, CPI, and wages, directly from the Bureau of Labor Statistics Public Data API. It provides tools to retrieve real-time economic time series data, browse popular series, and access survey metadata through natural language.
README
BLS MCP
An MCP (Model Context Protocol) server that wraps the Bureau of Labor Statistics Public Data API v2, letting Claude query U.S. labor statistics — employment, unemployment, wages, CPI, and more — directly from a conversation.
Disclaimer: This project is an independent, unofficial tool and is not affiliated with, endorsed by, or associated with the U.S. Bureau of Labor Statistics, the U.S. Department of Labor, or any government agency. All data is fetched in real time from the publicly available
api.bls.govAPI. The accuracy, completeness, and timeliness of the data are the sole responsibility of that API. This tool is provided for informational and research purposes only. Nothing returned by this server constitutes legal, financial, economic, or policy advice. Use responsibly and in accordance with applicable laws.
API status: The BLS Public Data API is at v0.0.2-beta and subject to change without notice. Tool behaviour may change as the upstream API evolves.
Available Tools
| Tool | Endpoint | Description |
|---|---|---|
get_single_series |
GET /timeseries/data/{id} |
Retrieve data for a single time series for the past three years |
get_latest_series |
GET /timeseries/data/{id}?latest=true |
Retrieve the most recent data point for a series |
get_multiple_series |
POST /timeseries/data/ |
Retrieve data for one or more series with optional parameters |
get_popular_series |
GET /timeseries/popular |
List the 25 most popular BLS series, optionally filtered by survey |
get_all_surveys |
GET /surveys |
List all BLS surveys with abbreviations and names |
get_survey |
GET /surveys/{abbr} |
Retrieve metadata for a single BLS survey |
Tool Parameters
get_single_series / get_latest_series
| Parameter | Type | Description |
|---|---|---|
series_id |
string | BLS series ID (uppercase, digits, _, -, #) |
get_multiple_series
| Parameter | Type | Required | Description |
|---|---|---|---|
series_ids |
string[] | Yes | Array of BLS series IDs (1–50) |
start_year |
string | No | Start year in YYYY format |
end_year |
string | No | End year in YYYY format |
catalog |
boolean | No | Include catalog data (requires API key) |
calculations |
boolean | No | Include net/percent change calculations (requires API key) |
annual_average |
boolean | No | Include annual averages (requires API key) |
aspects |
boolean | No | Include aspect data (requires API key) |
get_popular_series
| Parameter | Type | Required | Description |
|---|---|---|---|
survey |
string | No | 2-letter survey abbreviation (e.g. LA, CU, CE) |
get_survey
| Parameter | Type | Required | Description |
|---|---|---|---|
survey_abbreviation |
string | Yes | 2-letter survey abbreviation (e.g. TU, CU, LA) |
get_all_surveys — no parameters.
Series ID Format
BLS series IDs may contain uppercase letters, digits, underscores (_), dashes (-), and hashes (#). Lowercase letters and other special characters are not accepted. Examples:
LAUCN040010000000005— Local Area UnemploymentCUUR0000SA0— Consumer Price IndexCES0000000001— Current Employment StatisticsOEUN000000056--5747213213— Occupational Employment
Use get_popular_series or get_all_surveys to discover valid series IDs and survey abbreviations.
Registered vs. Unregistered Access
The BLS API works without an API key, but with reduced limits:
| Unregistered | Registered | |
|---|---|---|
| Daily query limit | 25 | 500 |
| Series per query | 25 | 50 |
| Year range | 10 years | 20 years |
| Optional parameters | No | catalog, calculations, annual averages, aspects |
Register for a free API key at https://data.bls.gov/registrationEngine/ and pass it via the BLS_API_KEY environment variable.
Prerequisites
- Node.js 18 or later
- npm 9 or later
- Claude Desktop (or any MCP-compatible client)
Installation
git clone https://github.com/larasrinath/bls_mcp.git
cd bls_mcp
npm install
npm run build
The compiled server lands in ./dist/index.js.
Claude Desktop Configuration
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json
Add the following block (adjust the path to match your machine):
{
"mcpServers": {
"bls": {
"command": "node",
"args": ["/absolute/path/to/bls_mcp/dist/index.js"],
"env": {
"BLS_API_KEY": "your-registration-key-here"
}
}
}
}
The env block is optional — omit it to use the API without a key (lower rate limits apply).
macOS/Linux example:
"args": ["/Users/yourname/Projects/bls_mcp/dist/index.js"]
Windows example:
"args": ["C:\\Users\\yourname\\Projects\\bls_mcp\\dist\\index.js"]
Restart Claude Desktop after saving. The six BLS tools will appear in the tool picker.
Bundled Skill
This repo includes a Claude skill at skills/bls-query/ that teaches Claude how to map natural language queries (e.g. "What's the current CPI?") to the correct BLS series IDs and tools — without guessing.
The skill includes a series catalog covering CPI, unemployment, employment, JOLTS, PPI, wages, productivity, and more (~100 common series IDs).
To install for Claude Code: Copy the skills/bls-query folder into ~/.claude/skills/.
To install for Claude.ai: Upload the skills/bls-query folder via Settings > Capabilities > Skills.
Example Prompts
- What is the current unemployment rate? (use
get_popular_seriesto find the series, thenget_latest_series) - Show me CPI data for the last 3 years using series CUUR0000SA0.
- Compare employment data for series CES0000000001 and CES3000000001 from 2020 to 2024.
- What BLS surveys are available?
- Tell me about the American Time Use survey.
- What are the most popular Local Area Unemployment series?
Development
# Run directly without building (uses tsx, included in devDependencies)
npm run dev
# Rebuild after changes
npm run build
Project Structure
bls_mcp/
├── src/
│ ├── index.ts # MCP server entry point
│ ├── client.ts # Typed BLS API client (axios)
│ └── tools/
│ ├── series.ts # get_single_series, get_latest_series, get_multiple_series
│ └── surveys.ts # get_popular_series, get_all_surveys, get_survey
├── skills/
│ └── bls-query/
│ ├── SKILL.md # Query workflow and tool selection guide
│ └── references/
│ └── series-catalog.md # ~100 common series ID mappings
├── package.json
├── tsconfig.json
├── LICENSE
└── README.md
Rate Limits
The BLS API enforces daily query limits (25 for unregistered, 500 for registered users). If you hit a rate limit, the server surfaces a clear error message rather than crashing silently. Register for a free API key to increase your limits.
License
MIT — see LICENSE.
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。