Shelpuk & Company
    Open Source
    MCP Server

    Kindly Web Search

    Web search + robust content retrieval for AI coding tools. The only web search MCP server that returns full page content, not just snippets. Built for Claude Code, Codex, Cursor, and other AI coding assistants.

    View on GitHub

    "Fantastic setup. Improved my Claude Code generation quality by 15–20% for our company’s commercial projects."

    Ostap Dribniuk
    Ostap DribniukSenior Software Engineer at Relevant Software

    Part of Our AI Coding Suite

    TDD for AI Agents orchestrates our complete open-source toolkit. It calls Kindly to verify assumptions and Lad to review designs and code — ensuring all three tools work together seamlessly.

    What Kindly Does Differently

    Full Conversation Retrieval

    Returns the complete thread: questions, answers, comments, reactions, and metadata in a single call.

    Direct API Integration

    Integrates with StackExchange, GitHub Issues, arXiv, and Wikipedia — presenting content in LLM-optimized formats.

    Real-Time Parsing

    Parses any webpage in real-time using a headless browser for cutting-edge issues posted yesterday.

    LLM-Ready Content

    Passes all useful content immediately — no need for a second scraping call. Clean Markdown output.

    MCP Tools

    web_search(query, num_results=3)

    Top results with title, link, snippet, and page_content (Markdown, best-effort).

    get_content(url)

    Full page_content (Markdown, best-effort) for any URL.

    One MCP Server to Rule Them All

    Kindly eliminates the need for multiple fragmented tools:

    Generic web search MCP servers
    StackOverflow MCP servers
    Web scraping MCP servers (Playwright, Puppeteer)
    Reduces reliance on GitHub MCP servers

    One Suite, Three Tools

    TDD for AI Agents is the orchestrator that ties our open-source AI coding tools into a complete development workflow. Each tool has a specific role.

    Supported AI Coding Assistants

    Codex (OpenAI)
    Claude Code
    Gemini CLI
    Cursor
    Claude Desktop
    GitHub Copilot (VS Code)
    Antigravity (Google IDE)

    Ready to supercharge your AI coding assistant?

    Deploy Kindly in your private cloud or hire the engineers who built it.

    Star on GitHub

    Frequently Asked Questions

    Answers to common questions about this topic.

    How can Kindly Web Search help AI coding agents find reliable web context?

    Open-source MCP server for privacy-first web search. Integrate real-time web results into your AI agents and LLM workflows. Shelpuk AI Technology Consulting builds this project to make AI-agent web context retrieval practical, predictable, and production-ready.

    How does the Kindly MCP architecture improve reliability over ad-hoc scraping workflows?

    The server standardizes web discovery and page extraction through explicit MCP tools, reducing fragile custom scripts and inconsistent data capture. Shelpuk AI Technology Consulting applies engineering patterns from client delivery to improve stability and maintainability of search workflows.

    How should teams deploy this project in private-cloud or enterprise environments?

    Recommended rollout includes controlled credentials, environment-based configuration, observability, and integration tests in the target MCP client stack. Shelpuk AI Technology Consulting helps teams deploy and govern MCP infrastructure in secure enterprise and private-cloud setups.

    What is the commercial model when organizations need production support around Kindly?

    There is no license fee for the core project; enterprise cost usually comes from integration engineering, hardening, and ongoing operational support. Shelpuk AI Technology Consulting offers consulting, implementation, and enablement services for organizations adopting this stack at scale.