skills.rest
reason-machines
reason-machinesOFFICIAL
Explore all skills by this author →
Website𝕏@reasonmachinesGitHub

kindly-web-search-mcp-server

Searches the web and extracts full structured content from StackOverflow, GitHub, Wikipedia, and arXiv.

7|2|Updated May 16, 2026
Search Tags:#web search#github issues#content extraction#MCP server#serper#StackOverflow#documentation lookup
One-click install
npx skills add https://github.com/reason-machines/mcp-skills --skill kindly-web-search-mcp-server-reason-machines
Or copy as Structured Prompt for Agent▼
Please help me install this Agent Skill.
Skill: kindly-web-search-mcp-server
Source: https://github.com/reason-machines/mcp-skills/tree/main/skills/kindly-web-search-mcp-server
Command: npx skills add https://github.com/reason-machines/mcp-skills --skill kindly-web-search-mcp-server-reason-machines

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve? AI coding assistants often receive only titles and URL snippets from basic search tools, forcing separate scraping steps to get actual answers. This Skill returns complete structured content—full StackOverflow threads, GitHub issue conversations, Wikipedia articles, and arXiv papers—in a single MCP call. ## Core Features & Use Cases - Web Search with Full Content: The web_search tool returns results with complete page content in Markdown, not just snippets, via Serper, Tavily, or self-hosted SearXNG. - URL Content Extraction: The get_content tool extracts clean Markdown from any URL using a headless Chromium browser that handles JavaScript-heavy sites. - Specialized Parsers: Automatically detects and optimally extracts StackOverflow Q&A threads, GitHub issues with all comments, Wikipedia articles, and arXiv papers. - Use Case: When debugging a "CUDA out of memory" error, ask the agent to search for solutions and receive complete StackOverflow threads with accepted answers, code examples, and community comments in one request. ## Quick Start Install uvx, set your SERPER_API_KEY environment variable, register the server with your MCP client, then ask the agent to search the web for FastAPI async database connection pooling best practices.

Frequently Asked Questions about kindly-web-search-mcp-server

High-intent search queries and answers about installing and using this skill.

FAQPage Schema
How do I set up a web search MCP server for Claude Desktop?▼

Install uvx, then add a kindly-web-search entry to your claude_desktop_config.json with the uvx command pointing to the GitHub repository. Set SERPER_API_KEY or TAVILY_API_KEY in the env block, and restart the client.

What search providers does this MCP server support?▼

It supports Serper, Tavily, and self-hosted SearXNG, checked in that priority order. Serper is recommended as the most reliable option; only one provider environment variable needs to be set.

Does web search extraction work on JavaScript-heavy websites?▼

Yes, generic webpages are rendered with a headless Chromium browser using nodriver, which handles JavaScript-heavy sites and extracts the main content area as clean Markdown. Chrome, Chromium, Edge, and Brave are auto-detected.

Why does GitHub content extraction hit rate limits?▼

GitHub's unauthenticated API has strict rate limits that cause 403 errors during issue extraction. Set a read-only GITHUB_TOKEN environment variable to avoid rate limits and get richer issue and discussion structure.

What are the limitations of automated web content extraction?▼

Extraction can return minimal content when sites block automated browsers, require authentication, or have JavaScript errors preventing rendering. Workarounds include using direct API endpoints or passing custom headers through SearXNG configuration.

Related Skills

Explore More Software Engineering Skills→
AradotsoAradotso
7

kindly-web-search-mcp-server

Searches web and extracts full pages to structured Markdown for AI coding workflows.

Official
Advanced
aquariuscookaquariuscook

QE Code Intelligence

Construct knowledge graphs and enable semantic search for codebases.

Community
Advanced
claude-office-skillsclaude-office-skills
368

Browser Automation

Automate web browser interactions for scraping, form filling, and testing with Puppeteer or Playwright.

Official
Advanced
ArdurAIArdurAI
1

god-systems-design

Guide distributed systems design and troubleshooting using CAP theorem and consensus algorithms.

Official
Advanced