mcp-wagewatch
MCP server over the U.S. Department of Labor Wage and Hour Division (WHD) enforcement dataset: employer wage-theft history, back wages owed, civil penalties, and affected-employee counts. Built for worker-justice nonprofits, legal-aid intake, and union researchers.
README
mcp-wagewatch
MCP server over the U.S. Department of Labor Wage and Hour Division (WHD) enforcement dataset: employer wage-theft history, back wages owed, civil penalties, and affected-employee counts. Built for worker-justice nonprofits, legal-aid intake, and union researchers.
The data is the WHISARD compliance-action dataset (every concluded WHD compliance action since FY2005) served from the DOL Open Data API. This server wraps the raw column names (trade_nm, bw_atp_amt, ee_violtd_cnt, ...) into clean, documented tool outputs.
Tools
| Tool | Arguments | Returns |
|---|---|---|
employer_violations |
employer (required), state, limit |
Enforcement cases matching the employer name, largest back wages first. Per case: employer, location, findings dates, back wages, civil penalties, employees affected, violation count. |
back_wages_summary |
employer and/or state (at least one), max_cases |
Aggregate totals across matching cases: total back wages, total employees affected, total civil penalties, case count, findings date range. |
violations_by_state |
state (required), naics, limit |
Top cases in a state where a violation was found, ordered by back wages. Optional NAICS-prefix industry filter. |
case_detail |
case_id (required) |
Full record for one case, including the per-statute breakdown (which laws were cited: FLSA, MSPA, H-1B, FMLA, Davis-Bacon, child labor, and so on). |
Data source
- Base URL:
https://apiprod.dol.gov/v4 - Query path:
GET /get/WHD/enforcement/json(agencyWHD, endpointenforcement, tableWHD_enforcement) - Auth: a free
X-API-KEY, sent only as a request header (never in the query string, so it stays out of URLs and logs). - Filtering: the
filter_objectquery parameter takes a JSON string withfield/operator/value(operatorseq,neq,gt,lt,in,not_in,like), composable withand/or. Paging vialimit/offset, ordering viasort_by/sort. - Scope: one row per concluded compliance action since FY2005.
Sources:
- DOL API User Guide (endpoint template, auth,
filter_objectsyntax): https://www.dataportal.dol.gov/pdf/dol-api-user-guide.pdf - Live dataset catalog (agency/endpoint identifiers): https://apiprod.dol.gov/v4/datasets
- Dataset landing page: https://catalog.data.gov/dataset/wage-and-hour-division-compliance-action-data
- WHISARD column dictionary: https://github.com/jeremybmerrill/whd/blob/master/lib/data/whd_data_dictionary.csv
Field map (WHISARD column to normalized output)
| WHISARD column | Normalized field |
|---|---|
case_id |
case_id |
trade_nm (fallback legal_name) |
employer |
legal_name |
legal_name |
street_addr_1_txt, cty_nm, st_cd, zip_cd |
location.{street,city,state,zip} |
naic_cd, naics_code_description |
naics_code, naics_description |
findings_start_date, findings_end_date |
findings_start_date, findings_end_date |
bw_atp_amt (total back wages agreed to pay) |
back_wages |
ee_violtd_cnt (employees employed in violation) |
employees_affected |
case_violtn_cnt (total case violations) |
violations |
sum of statute-level *_cmp_assd_amt |
civil_penalties |
cmp_assd_cnt (count of assessments) |
cmp_assessment_count (case_detail only) |
Notes:
- There is no single total-CMP-dollar column in WHISARD.
cmp_assd_cntis a count of assessments; the dollar penalties live in per-statute columns (flsa_cmp_assd_amt,mspa_cmp_assd_amt,h1b_cmp_assd_amt, and so on).civil_penaltiessums those. back_wages_summaryaggregates client-side (the API does not expose a group-by), over up tomax_casesmatching rows (default 1000). Ifcappedis true the totals are a floor.- Name search uses SQL
LIKEontrade_nmandlegal_name, wrapping the term as%term%. The term is uppercased defensively (WHD stores names largely in uppercase) andLIKEmetacharacters (%,_,\) are escaped so they match literally. See the caveats below.
Install
No build step. Runs directly on tsx.
git clone https://github.com/haksanlulz/mcp-wagewatch.git
cd mcp-wagewatch
npm install
API key
Register for a free DOL Open Data API key at https://dataportal.dol.gov/registration, then expose it as DOL_API_KEY:
export DOL_API_KEY=your-key-here # macOS / Linux
setx DOL_API_KEY your-key-here # Windows (new shells)
Without the key the tools return a clear error telling you to set it. The key is never logged.
MCP client config
Point your MCP client at index.ts via tsx. Use an absolute path.
{
"mcpServers": {
"wagewatch": {
"command": "npx",
"args": ["tsx", "/absolute/path/to/mcp-wagewatch/index.ts"],
"env": { "DOL_API_KEY": "your-key-here" }
}
}
}
Example
Call employer_violations with { "employer": "tyson", "state": "AR", "limit": 1 }:
{
"query": { "employer": "tyson", "state": "AR" },
"count": 1,
"cases": [
{
"case_id": "1234567",
"employer": "TYSON FOODS INC",
"legal_name": "TYSON FOODS INCORPORATED",
"location": { "street": "2200 DON TYSON PKWY", "city": "SPRINGDALE", "state": "AR", "zip": "72762" },
"naics_code": "311615",
"naics_description": "Poultry Processing",
"findings_start_date": "2021-01-01",
"findings_end_date": "2022-01-01",
"back_wages": 150000.5,
"civil_penalties": 7500,
"employees_affected": 88,
"violations": 12
}
]
}
Then pass a case_id to case_detail for the per-statute breakdown.
Caveats
The metadata endpoint is key-gated and this was built without a key, so:
- The column names are checked against the published WHISARD data dictionary (table
whd_whisard) and the dataset description, not against the liveWHD/enforcementmetadata endpoint (which requires the key). The v4enforcementendpoint is the same underlying WHISARD data, so the names are expected to match, but the exact live field list is unconfirmed. The normalizer is defensive: unknown-shaped values coerce tonullrather than throwing, and the CMP total scans every*_cmp_assd_amtcolumn present. LIKEcase-sensitivity on the DOL endpoint is unconfirmed, so the search term is uppercased defensively before the%term%wrap (WHD stores names largely in uppercase) andLIKEmetacharacters are escaped to match literally. If name searches still under-return, casing on the endpoint is the place to look.- Run
npm run smokewith a real key to confirm field names and behavior end to end before relying on output.
Develop
npm test # vitest, fetch mocked with the documented response shapes (no key needed)
npm run smoke # one live call per tool (needs DOL_API_KEY; skips cleanly without)
npm run typecheck
License
MIT. See LICENSE. Public U.S. government data from the U.S. Department of Labor. Unofficial, not affiliated with DOL.
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。