Skip to main content
Glama
enesjakozh
blazickjp

web-browser-mcp-server

by blazickjp
OverviewSchemaRelated ServersScoreDiscussions
Python

Twitter 关注 铁匠徽章 Python 版本 许可证：MIT PyPI 下载 PyPI 版本

✨ 特点

🌐 使 AI 助手能够通过简单的 MCP 界面浏览和提取网络上的内容。

Web 浏览器 MCP 服务器通过消息控制协议 (MCP) 为 AI 模型提供浏览网站、提取内容和理解网页的能力。它支持使用 CSS 选择器进行智能内容提取，并具备强大的错误处理功能。

🤝**贡献• 📝报告错误**

Related MCP server: mcp-web-tools

✨ 核心功能

  • 🎯智能内容提取：使用 CSS 选择器准确定位您需要的内容

  • ⚡闪电般快速：采用异步处理构建，以实现最佳性能

  • 📊丰富的元数据：捕获标题、链接和结构化内容

  • 🛡️强大且可靠：内置错误处理和超时管理

  • 🌍跨平台：可在 Python 运行的任何地方使用

🚀 快速入门

通过 Smithery 安装

要通过Smithery自动安装 Claude Desktop 的 Web 浏览器服务器：

npx -y @smithery/cli install web-browser-mcp-server --client claude

手动安装

使用 uv 安装：

uv tool install web-browser-mcp-server

对于开发：

# Clone and set up development environment
git clone https://github.com/blazickjp/web-browser-mcp-server.git
cd web-browser-mcp-server

# Create and activate virtual environment
uv venv
source .venv/bin/activate

# Install with test dependencies
uv pip install -e ".[test]"

🔌 MCP 集成

将此配置添加到您的 MCP 客户端配置文件中：

{
    "mcpServers": {
        "web-browser-mcp-server": {
            "command": "uv",
            "args": [
                "tool",
                "run",
                "web-browser-mcp-server"
            ],
            "env": {
                "REQUEST_TIMEOUT": "30"
            }
        }
    }
}

对于开发：

{
    "mcpServers": {
        "web-browser-mcp-server": {
            "command": "uv",
            "args": [
                "--directory",
                "path/to/cloned/web-browser-mcp-server",
                "run",
                "web-browser-mcp-server"
            ],
            "env": {
                "REQUEST_TIMEOUT": "30"
            }
        }
    }
}

💡 可用工具

服务器提供了强大的网页浏览工具：

浏览网页

使用可选的 CSS 选择器浏览网页并提取内容：

# Basic webpage fetch
result = await call_tool("browse_webpage", {
    "url": "https://example.com"
})

# Target specific content with CSS selectors
result = await call_tool("browse_webpage", {
    "url": "https://example.com",
    "selectors": {
        "headlines": "h1, h2",
        "main_content": "article.content",
        "navigation": "nav a"
    }
})

⚙️ 配置

通过环境变量配置：

多变的

目的

默认

REQUEST_TIMEOUT

网页请求超时（秒）

三十

🧪 测试

运行测试套件：

python -m pytest

📄 许可证

根据 MIT 许可证发布。详情请参阅许可证文件。

由 Pear Labs 团队倾情打造

Install Server
A
license - permissive license
B
quality
D
maintenance

How are these scores calculated?

Maintenance

–Maintainers
–Response time
–Release cycle
–Releases (12mo)
Commit activity

Resources

Unclaimed servers have limited discoverability.

Looking for Admin?

If you are the server author, to access and configure the admin panel.

Tools

Related MCP Servers

  • Tagny MCP Server

    tagny
    A
    license
    Not graded
    quality
    C
    maintenance
    Enables web browsing capabilities for locally served LLMs through URL text fetching, link extraction, and web search using Brave and DuckDuckGo engines. Designed to enhance LLMs with real-time web access through the MCP protocol.
    MIT

  • web-search

    sh-arman
    A
    license
    Not graded
    quality
    D
    maintenance
    Enables web searching using Google search results with no API keys required.
    23
    MIT

View all related MCP servers

Related MCP Connectors

  • Aginx Browser

    Stealth web browser for agents: search, fetch, click and type through persistent sessions over MCP.

  • Pagewatch

    Read a URL as clean markdown, screenshot a website, url to PDF. Web access for agents, no signup.

  • browserbasehq-mcp-browserbase

    Provides cloud browser automation capabilities using Stagehand and Browserbase, enabling LLMs to i…

View all MCP Connectors

Appeared in Searches

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/blazickjp/web-browser-mcp-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server