light-research-mcp

Code-Hex/light-research-mcp

3.4

If you are the rightful owner of light-research-mcp and would like to certify it and/or have it hosted online, please leave a comment on the right or send an email to henry@mcphub.com.

A lightweight MCP server for LLM orchestration that provides efficient web content search and extraction capabilities.

The LLM Researcher is a lightweight Model Context Protocol (MCP) server designed to facilitate seamless integration with Large Language Models (LLMs). It offers efficient web content search and extraction capabilities, allowing LLMs to access and process web data effectively. Built with modern development tools like TypeScript, tsup, and vitest, this server supports multiple modes of operation, including CLI, MCP server, and interactive modes. It leverages DuckDuckGo for web searches and GitHub for code searches, ensuring cost-free operations. The server also employs Playwright and @mozilla/readability for smart content extraction, providing LLM-optimized output in sanitized Markdown format. With cross-platform compatibility and type-safe implementation, the LLM Researcher is a versatile tool for developers and researchers working with LLMs.

Features

  • MCP Server Support: Provides Model Context Protocol server for LLM integration.
  • Free Operation: Utilizes DuckDuckGo HTML endpoint, avoiding API costs.
  • Smart Content Extraction: Uses Playwright and @mozilla/readability for clean content.
  • LLM-Optimized Output: Produces sanitized Markdown with essential formatting.
  • Cross-Platform: Compatible with macOS, Linux, and WSL.

Usages

usage with Claude Code

bash
# Add as an MCP server to Claude Code
claude mcp add light-research-mcp /path/to/light-research-mcp/dist/bin/llmresearcher.js --mcp

# Or with project scope for team sharing
claude mcp add light-research-mcp -s project /path/to/light-research-mcp/dist/bin/llmresearcher.js --mcp

# List configured servers
claude mcp list

# Check server status
claude mcp get light-research-mcp

usage with Command Line Interface

bash
# Search mode - Search DuckDuckGo and interactively browse results
llmresearcher "machine learning transformers"

# GitHub Code Search mode - Search GitHub for code
llmresearcher -g "useState hooks language:typescript"

# Direct URL mode - Extract content from specific URL
llmresearcher -u https://example.com/article

# Interactive mode - Enter interactive search session
llmresearcher

# Verbose logging - See detailed operation logs
llmresearcher -v "search query"

# MCP Server mode - Start as Model Context Protocol server
llmresearcher --mcp

Tools

  1. github_code_search

    Search GitHub repositories for code examples and implementation patterns.

  2. duckduckgo_web_search

    Search the web with DuckDuckGo.

  3. extract_content

    Extract detailed content from URLs.