首页/MCP Server 目录/Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server

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

❌ 实测失败serverPythonMIT★ 404

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.

实测结果

失败

沙箱内启动/握手失败，下方给出失败阶段与原始报错。失败阶段：—，错误类型：install_failed。这类信息对判断“是不是我这边的环境问题”很有用，原始报错见下。

error_type: install_failed

__PIP_RC__=1
__INSTALL_DONE__
__PYDIST_MISS__
Using CPython 3.12.16 interpreter at: /usr/local/bin/python3.12
Creating virtual environment at: venv
Using Python 3.12.16 environment at: venv
error: No solution found when resolving dependencies
  cause: Because kindly-web-search-mcp-server was not found in the package registry and you require kindly-web-search-mcp-server, we can conclude that your requirements are unsatisfiable.

安装方式: uvx
包名: kindly-web-search-mcp-server
解析依据: pyproject.toml name
沙箱: docker
总耗时: 1958 ms
安装耗时: 1958 ms
探针版本: 1.0.0
实测时间: 2026-11-11 16:43:31

如何使用

❌ 实测失败install_failed · __PIP_RC__=1；下面配置仅供参考，跑不跑得通取决于你的环境

1安装 / 启动命令uv / uvx

uvx kindly-web-search-mcp-server

2客户端配置Claude Desktop / Cursor

{
  "mcpServers": {
    "shelpuk-ai-technology-consulting-kindly-web-search-mcp-server": {
      "command": "uvx",
      "args": [
        "kindly-web-search-mcp-server"
      ]
    }
  }
}

整段粘进 claude_desktop_config.json 的 mcpServers 里（Cursor 用 ~/.cursor/mcp.json），保存后重启客户端。

安装方式来源：pyproject.toml name，沙箱实测未通过。

打开 GitHub 仓库 ↗项目主页 ↗MCP 体检工具

仓库信息

全名: Shelpuk-AI-Technology-Consulting/kindly-web-search-mcp-server
分类: server
Stars: 404
Forks: 37
主要语言: Python
License: MIT
最近推送: 2026-10-19
仓库创建: 2026-01-02
首次收录: 2026-11-10
最近抓取: 2026-11-10

#ai#ai-agents#ai-tools#claude-code#codex#gemini#github-copilot#hermes#hermes-agent#mcp-server#openclaw#openclaw-extension