kindly-web-search-mcp-server
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents
What is kindly-web-search-mcp-server?
Kindly Web Search MCP Server: Web search + robust content retrieval for AI coding tools (Claude Code, Codex, Cursor, GitHub Copilot, Gemini, etc.) and AI agents (Claude Desktop, OpenClaw, Hermes, etc.). Supports Serper, Tavily, and SearXNG.
Overview of kindly-web-search-mcp-server
What it is
Kindly Web Search MCP Server is a web search and content retrieval tool for AI coding assistants and agents. It is part of the Shelpuk AI Technology Consulting agentic suite. It works with Claude Code, Codex, Antigravity, Cursor, Windsurf, and any agent that supports skills or MCP servers. The server provides two tools: web_search and get_content. It integrates with APIs for StackExchange, GitHub Issues, arXiv, and Wikipedia, and parses any webpage in real-time using a headless browser. It supports multiple search providers including Serper, SerpBase, Tavily, SearXNG, Sofya, You.com, and Serply.
Key features
- Integrates directly with APIs for StackExchange, GitHub Issues, arXiv, and Wikipedia, presenting content in LLM-optimized formats with proper structure.
- Returns the full conversation in a single call: questions, answers, comments, reactions, and metadata.
- Parses any webpage in real-time using a headless browser for cutting-edge issues that were literally posted yesterday.
- Passes all useful content to the LLM immediately - no need for a second scraping call.
- Supports multiple search providers (Serper, SerpBase, Tavily, SearXNG, Sofya, You.com, and Serply) with intelligent fallback.
- Provides Markdown fast paths for doc sites before launching the headless browser.
- Supports proxy environment variables (
HTTP_PROXY,HTTPS_PROXY,ALL_PROXY) forhttpx-based handlers andKINDLY_CHROME_PROXYfor the universal HTML loader.
Use cases
Debugging cryptic errors in cloud services (e.g., Google Cloud Batch with GPU instances) by retrieving full StackOverflow threads with answers and comments.Searching for up-to-date API and package documentation via web search.Retrieving structured content from GitHub Issues, GitHub Discussions, Wikipedia, and arXiv papers.Improving code quality produced by AI coding agents by providing relevant web content in a single call.
Getting started
See the repository README for installation and configuration instructions.
License and pricing
This project is licensed under the MIT License. It is open source.
Based on the project's public README and repository metadata.