Web Research MCP Server
由 MEOK AI Labs 提供 — 为每个人打造的主权 AI 工具。
Web Research MCP Server
面向 AI 智能体的网络搜索和浏览器自动化工具包。通过 DuckDuckGo 搜索网络(无需 API 密钥),使用无头 Chromium 浏览页面、提取文章内容、截取屏幕截图、与表单交互,并运行自动搜索和阅读多个页面的多步研究工作流。
工具
工具 | 描述 |
| DuckDuckGo 搜索 -- 无需 API 密钥 |
| 全功能浏览器自动化:提取、截图、点击、输入、PDF |
| 纯净文章提取(去除导航/广告/样板内容) |
| 多步工作流:搜索 + 阅读前 N 个页面 + 汇总简报 |
| 任意地点的当前天气 (wttr.in) |
安装
pip install mcp httpx playwright duckduckgo-search
python -m playwright install chromiumduckduckgo-search 包是可选的 -- 如果未安装,服务器将回退到 HTML 抓取。browse_page、extract_article 和 research_topic 需要 Playwright + Chromium。
使用方法
运行服务器
python server.pyClaude Desktop 配置
{
"mcpServers": {
"web-research": {
"command": "python",
"args": ["/path/to/web-research-mcp/server.py"]
}
}
}调用示例
网络搜索:
Tool: web_search
Input: {"query": "best practices for MCP server development", "limit": 5}
Output: {"results": [{"title": "...", "url": "...", "snippet": "..."}], "query": "...", "engine": "duckduckgo"}浏览并提取页面:
Tool: browse_page
Input: {"url": "https://example.com/article", "action": "extract"}
Output: {"status": "ok", "title": "...", "text": "...", "links": [...]}截取屏幕截图:
Tool: browse_page
Input: {"url": "https://example.com", "action": "screenshot"}
Output: {"status": "ok", "image_base64": "...", "full_size_bytes": 142531}研究主题(自动化):
Tool: research_topic
Input: {"query": "MCP protocol specification 2026", "depth": 3}
Output: {"pages_searched": 5, "pages_read": 3, "sources": [...], "brief": "# Research: ..."}定价
层级 | 限制 | 价格 |
免费版 | 25 次调用/天 | $0 |
专业版 | 无限制 + 全功能截图 + PDF 导出 | $9/月 |
企业版 | 定制 + 代理轮换 + 验证码破解 | 联系我们 |
许可证
MIT
This server cannot be installed
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Latest Blog Posts
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/CSOAI-ORG/web-research-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server