# Light Research

> Use this tool when you need to efficiently search and extract web content, such as documentation or code examples, without incurring API costs. It solves problems like accessing clean and structured content from web pages, and supports both interactive and programmatic usage. The tool takes web queries as input and outputs clean Markdown content, making it ideal for AI assistants and production use cases that require reliable web research capabilities.

Canonical page: https://skillsregistry.net/skills/light-research  
JSON: https://api.skillsregistry.net/v1/skills/light-research

## Description

This lightweight MCP server by Code-Hex provides efficient web content search and extraction capabilities through DuckDuckGo's HTML endpoint and GitHub's Code Search API, eliminating API costs while delivering clean, LLM-optimized content. The implementation combines Playwright-based browser automation with Mozilla's Readability library and DOMPurify sanitization to extract and convert web content into clean Markdown format, supporting both interactive CLI usage and programmatic integration. It's particularly valuable for AI assistants that need to research documentation, find code examples, and extract structured content from web pages with built-in rate limiting, locale support, and robust error handling for production use cases.

## Trust

- **Trust score (0–1):** 0.86
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** version-control
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/light-research)
- **Repository:** <https://github.com/code-hex/light-research-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "light-research"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/light-research` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/light-research/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt