/ 目录 / 演练场 / kindly-web-search-mcp-server
← 全部服务器 ↗ GitHub
● 社区 Shelpuk-AI-Technology-Consulting ⚡ 即开即用

kindly-web-search-mcp-server

作者 Shelpuk-AI-Technology-Consulting · Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server

Web search that returns full conversations (entire SO threads, GitHub issues with comments) — not just snippets you have to re-fetch.

Kindly Web Search MCP pairs search (Serper/Tavily/SearXNG) with robust content retrieval that understands platforms like StackOverflow, GitHub Issues, and arXiv. Instead of snippets that force second-round fetches, tools return the full conversation in one call.

▶ 观看演示 📦 安装 💡 使用场景

为什么要用

核心特性

实时演示

实际使用效果

kindly-web-search.replay ▶ 就绪
0/0

安装

选择你的客户端

~/Library/Application Support/Claude/claude_desktop_config.json  · Windows: %APPDATA%\Claude\claude_desktop_config.json
{
  "mcpServers": {
    "kindly-web-search": {
      "command": "uvx",
      "args": [
        "kindly-web-search-mcp-server"
      ],
      "_inferred": true
    }
  }
}

打开 Claude Desktop → Settings → Developer → Edit Config。保存后重启应用。

~/.cursor/mcp.json · .cursor/mcp.json
{
  "mcpServers": {
    "kindly-web-search": {
      "command": "uvx",
      "args": [
        "kindly-web-search-mcp-server"
      ],
      "_inferred": true
    }
  }
}

Cursor 使用与 Claude Desktop 相同的 mcpServers 格式。项目级配置优先于全局。

VS Code → Cline → MCP Servers → Edit
{
  "mcpServers": {
    "kindly-web-search": {
      "command": "uvx",
      "args": [
        "kindly-web-search-mcp-server"
      ],
      "_inferred": true
    }
  }
}

点击 Cline 侧栏中的 MCP Servers 图标，然后选 "Edit Configuration"。

~/.codeium/windsurf/mcp_config.json
{
  "mcpServers": {
    "kindly-web-search": {
      "command": "uvx",
      "args": [
        "kindly-web-search-mcp-server"
      ],
      "_inferred": true
    }
  }
}

格式与 Claude Desktop 相同。重启 Windsurf 生效。

~/.continue/config.json
{
  "mcpServers": [
    {
      "name": "kindly-web-search",
      "command": "uvx",
      "args": [
        "kindly-web-search-mcp-server"
      ]
    }
  ]
}

Continue 使用服务器对象数组，而非映射。

~/.config/zed/settings.json
{
  "context_servers": {
    "kindly-web-search": {
      "command": {
        "path": "uvx",
        "args": [
          "kindly-web-search-mcp-server"
        ]
      }
    }
  }
}

加入 context_servers。Zed 保存后热重载。

claude mcp add kindly-web-search -- uvx kindly-web-search-mcp-server

一行命令搞定。用 claude mcp list 验证，claude mcp remove 卸载。

使用场景

实战用法： kindly-web-search-mcp-server

Debug a library error by reading the whole StackOverflow thread

👤 Developers hit with a cryptic error ⏱ ~10 min beginner

何时使用： The top SO answer is often not right; the conversation below has the real fix.

前置条件
  • SERPER_API_KEY — serper.dev — 2500 free queries/mo
步骤
  1. Search the exact error
    Search for: 'fatal error: 'openssl/opensslv.h' file not found' arm64 mac — return the top 3 SO URLs.✓ 已复制
    → SO URLs with snippets
  2. Fetch the full thread of the most relevant
    get_content on the top SO URL — give me the whole thread including every comment.✓ 已复制
    → Full Q+A+comments in Markdown
  3. Pick the fix the thread's consensus supports
    Which answer (including ones below the accepted one) does the thread's comments actually validate? Show me the exact commands.✓ 已复制
    → Specific command sequence

结果： The real fix, not just the accepted answer — with evidence from comments.

注意事项
  • SO pages can be huge; full content can be 10k+ tokens — Ask for an executive summary first, then drill in
搭配使用： filesystem

Read a long GitHub Issue with full context

👤 Engineers evaluating whether to upgrade a dependency ⏱ ~10 min beginner

何时使用： The issue has 80 comments and you need the signal from the noise.

前置条件
  • GITHUB_TOKEN (optional but recommended) — A classic/fine-grained token; empty scope set fine for public repos
步骤
  1. Pull structured issue data
    get_content on https://github.com/vercel/next.js/issues/12345 — return structured metadata plus body and all comments.✓ 已复制
    → Structured extract, not raw HTML
  2. Distill signal
    Summarize: is this fixed, open, workaround-only? Who from the maintainer team has commented, and what was their last position?✓ 已复制
    → Status + maintainer stance

结果： A grounded go/no-go decision on a library upgrade.

搭配使用： github

Summarize an arXiv paper with full text access

👤 Researchers, curious devs ⏱ ~10 min beginner

何时使用： You don't want a snippet; you want to quote section 3.2.

步骤
  1. Fetch the paper
    get_content https://arxiv.org/abs/2410.XXXXX — full text.✓ 已复制
    → Markdown of the paper
  2. Targeted summary
    Summarize the methodology (section 3) in 5 bullets and quote the key claim from the results table.✓ 已复制
    → Summary with verbatim quote

结果： Paper understanding without leaving chat.

组合

与其他 MCP 搭配，撬动十倍杠杆

kindly-web-search + github

Kindly reads the issue discussion; github MCP creates a tracking issue in your own repo

Read the discussion on open-upstream/project#432 via kindly, then open a shadowing issue in our team's repo summarizing it.✓ 已复制
kindly-web-search + filesystem

Save researched answers as Markdown notes

Research 'best practices for Postgres connection pooling with pgbouncer', save the full SO thread + two docs links under ./notes/pgbouncer.md.✓ 已复制

工具

此 MCP 暴露的能力

工具输入参数何时调用成本
web_search query: str, num_results?: int (default 3) Any web search where you'd have followed with a fetch anyway 1 search provider call + N fetches
get_content url: str Deep dive on a specific URL 1 fetch (plus provider ops for platform parsing)

成本与限制

运行它的成本

API 配额
Serper: 2500/mo free. Tavily: 1000/mo free. SearXNG self-hosted: unlimited.
每次调用 Token 数
web_search with full content: 2-6k per call. get_content: 1-10k depending on page.
费用
Free with provider free tiers; self-host SearXNG for zero cost
提示
For iterative research, lower num_results to 2 — kindly returns full content per result, so 3 can be expensive.

安全

权限、密钥、影响范围

凭据存储： Env vars: SERPER_API_KEY or TAVILY_API_KEY or SEARXNG_BASE_URL
数据出站： Queries to chosen search provider + fetches to result URLs
切勿授予： GitHub token with repo write — public-read is enough for content extraction

故障排查

常见错误与修复

No provider configured

Set at least one of SERPER_API_KEY, TAVILY_API_KEY, or SEARXNG_BASE_URL.

验证： env | grep -E 'SERPER|TAVILY|SEARXNG'
Chromium not found

Install Chrome, Edge, Brave, or chromium. Set PUPPETEER_EXECUTABLE_PATH if auto-detect fails.

验证： which google-chrome || which chromium
Python version error

Requires Python 3.13+. Upgrade via pyenv or uv.

验证： python3 --version

替代方案

kindly-web-search-mcp-server 对比其他方案

替代方案何时用它替代权衡
omnisearchYou want many providers including AI-search in one MCPLess platform-aware; snippets-first
brave-searchYou only want search, not full-content retrievalSnippets only
fetch MCPYou don't need search, just URL fetchingNo search

更多

资源

📖 阅读 GitHub 上的官方 README

🐙 查看未解决的 issue

🔍 浏览全部 400+ MCP 服务器和 Skills