연결

Kempt Horizon Data Toolkit

PhantasyxbyPhantasyx
•
개발자 도구
데이터 과학 및 ML
웹 스크래핑 및 데이터 수집

Extract clean Markdown from web pages, sanitize messy datasets, and query live US government records including SEC EDGAR and Grants.gov.

Kempt Horizon Data Toolkit is a hosted, read-only MCP server that equips AI agents with 17 specialized data retrieval and transformation tools. It streamlines AI workflows by converting web pages into LLM-ready Markdown, validating and sanitizing unstructured inputs like emails, phone numbers, and CSVs, and providing direct programmatic access to live US federal data sources such as SEC EDGAR, the Federal Register, USAspending, and Grants.gov.

주요 기능

010 GitHub stars
02Web-to-Markdown conversion, page metadata extraction, and targeted scraping
03Data cleaning utilities for email validation, phone parsing, text sanitization, and CSV formatting
04SEC EDGAR search for company filings, financial statements, and corporate profiles
05US federal data access covering Federal Register notices, USAspending awards, and Grants.gov
06Cloud-hosted implementation requiring zero local installation via Streamable HTTP

사용 사례

01Conducting corporate and financial due diligence using live SEC EDGAR filing data
02Scraping and converting web content into clean Markdown for LLM analysis and context injection
03Sanitizing raw user contact inputs and structured CSV files before ingestion into databases or pipelines