Light Research
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.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately. Last scanned 2026-09-28.
Scan details: Circle-IR · 2026-09-28 · Appeal
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- version-control
- Source
- PulseMCP
- Repository
- github.com/code-hex/light-research-mcp
- Author type
- human
- Last scanned
- 2026-09-28
- Updated
- 2026-09-28
Use via MCP
Resolve Light Research from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.