WebSearch - Advanced Web Search and Content Extraction Tool MCP…

@m4s1t4

代码仓库

基本信息

分类

搜索

传输方式

stdio

作者

m4s1t4

关于 WebSearch - Advanced Web Search and Content Extraction Tool MCP Server

Web Search tools are a series of tools that allow Claude to acces de internet via MCP Server

#websearch #content-extraction #web-scraping

WebSearch - Advanced Web Search and Content Extraction Tool MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "webSearch-Tools": {
      "command": "uv",
      "args": [
        "venv"
      ]
    }
  }
}

WebSearch - Advanced Web Search and Content Extraction Tool MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is WebSearch - Advanced Web Search and Content Extraction Tool?

A Python-based web search and content extraction tool that leverages the Firecrawl API for advanced web scraping, searching, and content analysis. It is built as a Model Context Protocol (MCP) server for seamless integration with MCP clients.

How to use WebSearch - Advanced Web Search and Content Extraction Tool?

Install the uv package manager, clone the repository, create a virtual environment, install dependencies with uv sync, and set required environment variables (Firecrawl API key, optionally OpenAI and Tavily keys). Then configure the MCP server in Claude for Desktop’s claude_desktop_config.json by adding the server command pointing to main.py. The server exposes four tools: Search, Extract, Crawl, and Scrape.

Key features of WebSearch - Advanced Web Search and Content Extraction Tool

Advanced Web Search with customizable parameters
Content extraction using natural language prompts
Web crawling with configurable depth and limits
Web scraping supporting multiple output formats
MCP integration for seamless tool access

Use cases of WebSearch - Advanced Web Search and Content Extraction Tool

Perform intelligent web searches and retrieve structured results
Extract specific information from web pages via natural language prompts
Crawl websites with configurable depth and page limits
Scrape web pages and optionally capture screenshots

常见问题

What API keys are required?

Firecrawl API key is required; OpenAI and Tavily API keys are optional for enhanced features.

How do I configure the server for Claude for Desktop?

Add the server to your `claude_desktop_config.json` with the command `uv --directory /absolute/path/to/WebSearch run main.py`.

What should I do if I encounter errors?

Ensure all required API keys are set in the `.env` file, verify they are valid and not expired, and check that the `.env` file is in the project root directory.

What are the runtime dependencies?

Python 3.8+, the `uv` package manager, and the Firecrawl API (with optional OpenAI and Tavily APIs).

搜索分类下的更多 MCP 服务器

CardsNearby

MCP server for CardsNearby — find local US card shops and card shows (sports, Pokémon, Magic, TCG) by location.

VerifyAPI

Circuit Savers LLC

Fact-check any claim with live web sources. Ed25519-signed receipts. Catches hallucinations.

Thordata MCP Server

Thordata

Thordata MCP Server gives AI agents real-time access to Google, Bing, DuckDuckGo, and Yandex search through one MCP connection. It supports structured results, geo-targeting, language and device parameters, SEO monitorin

3gpp-mcp

higebu

An MCP (Model Context Protocol) server that makes 3GPP specifications accessible to LLMs.

patent-literature-search-mcp

patsnap

A professional tool for searching Patsnap’s global patent and literature databases using natural language, semantic, or keyword queries. It supports precise filtering and retrieves bibliographic data in Markdown format.