Is Crawl Mcp safe to use?

Crawl Mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.

How do I install Crawl Mcp?

Crawl Mcp supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.

What AI clients work with Crawl Mcp?

Crawl Mcp is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.

Is Crawl Mcp actively maintained?

Crawl Mcp is less actively maintained — last commit was 345 days ago. It has 38 GitHub stars.

Crawl Mcp

Name: Crawl Mcp
Author: wutongci

crawl-mcp-server · by wutongci

完整的微信文章抓取MCP服务器 - 基于Model Context Protocol (MCP)的智能网页抓取工具，专为Cursor IDE和AI工具设计。

38 0 tools GitHub npm

No known CVEs

MIT license

Stale

Last commit 345d ago

Works with most clients

Transport: stdio, http

0 tools

Grade F

Edit this pageView history

Browser

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "crawl-mcp": {
      "args": [
        "-y",
        "crawl-mcp-server"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/crawl-mcp)](https://mcppedia.org/s/crawl-mcp)

Read me

What Crawl Mcp does

🚀 真正能下载图片的微信文章抓取工具 - 基于Model Context Protocol (MCP)的智能抓取服务器，专为Cursor IDE和AI工具设计。

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y 'crawl-mcp-server' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

49/100across 5 weighted dimensions

How we score →

0255075100

−51

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked crawl-mcp-server against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Crawl Mcp safe to use?: Crawl Mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install Crawl Mcp?: Crawl Mcp supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with Crawl Mcp?: Crawl Mcp is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.
Is Crawl Mcp actively maintained?: Crawl Mcp is less actively maintained — last commit was 345 days ago. It has 38 GitHub stars.

Similar servers

Others in browser

View all →

Puppeteer MCP Server95

Browser automation with Puppeteer for web scraping and testing

86.5k 5

Firecrawl Mcp Server95

🔥 Official Firecrawl MCP Server - Adds powerful web scraping and search to Cursor, Claude and any other LLM clients.

6.4k 4

Firecrawl Mcp95

MCP server for Firecrawl — search, scrape, and interact with the web. Supports both cloud and self-hosted instances. Features include web search, scraping, page interaction, batch processing, and LLM-powered content analysis.

6.4k 5

Apify Mcp Server94

The Apify MCP server enables your AI agents to extract data from social media, search engines, maps, e-commerce sites, or any other website using thousands of ready-made scrapers, crawlers, and automation tools available on the Apify Store.

1.3k 1

MCP Security Weekly

Get CVE alerts and security updates for Crawl Mcp and similar servers.

Community

Discussion

Start a conversation

Ask a question, share a tip, or report an issue.

Has anyone used this with Cursor?How do you handle auth?Any alternatives?

Edit this pageView history

Browser

Step 1

Install in your client

Config is the same across clients — only the file and path differ.

Supported in Claude Desktopstdio, http · Node 18+

Paste into ~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "crawl-mcp": {
      "args": [
        "-y",
        "crawl-mcp-server"
      ],
      "command": "npx"
    }
  }
}

Are you the author?

Add this badge to your README to show your security score and help users find safe servers.

Embed in your READMEAbout badges →

[![MCPpedia Score](https://mcppedia.org/api/badge/crawl-mcp)](https://mcppedia.org/s/crawl-mcp)

Read me

What Crawl Mcp does

🚀 真正能下载图片的微信文章抓取工具 - 基于Model Context Protocol (MCP)的智能抓取服务器，专为Cursor IDE和AI工具设计。

Test This Server

Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.

npx -y 'crawl-mcp-server' 2>&1 | head -1 && echo "✓ Server started successfully"

After testing, let us know if it worked:

README

Crawl-MCP Server

🚀 真正能下载图片的微信文章抓取工具 - 基于Model Context Protocol (MCP)的智能抓取服务器，专为Cursor IDE和AI工具设计。

🎉 v1.1.0 重大升级：从"指令生成器"升级为"真正下载工具"，支持完整的图片本地化！

✨ 主要特性

🎯 核心功能 (v1.1.0)

真正的图片下载: ✅ 实际下载微信图片，不只是生成指令
双模式设计: 指令模式（学习用）+ 自动模式（效率用）
完整本地化: 图片下载 + 路径更新 + 离线可用的Markdown文档
智能处理: 微信域名识别、正确Headers、并发控制、重试机制

🔧 技术特色 (v1.1.0)

专业图片处理:
- 🎯 微信图片域名识别（mmbiz.qpic.cn）
- 🎯 正确的HTTP Headers（Referer, User-Agent）
- 🎯 wx_fmt参数处理（jpeg, png, gif）
- 🎯 并发控制（同时下载3张）+ 重试机制
MCP协议支持: 完整的Model Context Protocol实现
模块化架构: ImageDownloader + ArticleProcessor + CrawlTool
TypeScript支持: 完整的类型定义和编译支持
Node.js 18+: 使用内置fetch API，无额外HTTP库依赖

🎮 Cursor IDE集成

一键安装: npx crawl-mcp-server@1.1.0
开箱即用: 无需复杂配置，直接可用
AI工具支持: 在Cursor中直接使用AI进行完整抓取
工具自动识别: Agent自动调用相关抓取工具

🚀 快速开始

💻 安装使用

方法1: npx直接运行（推荐）

# 使用最新的v1.1.0版本
npx crawl-mcp-server@1.1.0

方法2: 全局安装

npm install -g crawl-mcp-server@1.1.0
crawl-mcp-server

方法3: 项目本地安装

npm install crawl-mcp-server@1.1.0
npx crawl-mcp-server

💡 提示: 推荐使用 @1.1.0 版本，确保获得最新的图片下载功能

🔌 Cursor IDE配置

创建MCP配置文件 在项目根目录创建 .cursor/mcp.json:

{
  "mcpServers": {
    "crawl-mcp": {
      "command": "npx",
      "args": ["-y", "crawl-mcp-server@1.1.0"],
      "env": {
        "NODE_ENV": "production"
      }
    }
  }
}

重启Cursor 重启Cursor让配置生效

开始使用 在Cursor中直接使用AI助手进行网页抓取：

指令模式（学习推荐）：

请使用crawl mcp抓取这篇微信文章：https://mp.weixin.qq.com/s/xxxxx

自动模式（效率优先）：

我已经获取了HTML内容，请使用crawl mcp自动模式处理并下载图片

🛠️ MCP工具说明

1. crawl_wechat_article

单篇文章抓取工具

参数:

url (必需): 微信文章链接
outputFormat (可选): 输出格式 (markdown/json/html，默认: markdown)
strategy (可选): 抓取策略 (basic/conservative/fast，默认: basic)
includeImages (可选): 是否包含图片 (默认: true)

示例:

{
  "url": "https://mp.weixin.qq.com/s/example123",
  "outputFormat": "markdown",
  "strategy": "basic",
  "includeImages": true
}

2. crawl_wechat_batch

批量文章抓取工具

参数:

urls (必需): 文章链接数组
outputFormat (可选): 输出格式
strategy (可选): 抓取策略
maxConcurrent (可选): 最大并发数 (默认: 3)

示例:

{
  "urls": [
    "https://mp.weixin.qq.com/s/example1",
    "https://mp.weixin.qq.com/s/example2"
  ],
  "outputFormat": "markdown",
  "maxConcurrent": 2
}

3. crawl_get_status

状态查询工具

参数:

sessionId (可选): 会话ID，不提供则返回所有会话状态

⚙️ 抓取策略说明

策略	速度	稳定性	适用场景
fast	⚡ 最快	🔸 一般	网络良好，页面简单
basic	🚀 中等	⭐ 平衡	大多数情况（推荐）
conservative	🐌 较慢	💎 最稳定	网络不稳定，复杂页面

📦 项目结构

crawl-mcp/
├── src/
│   ├── core/              # 核心模块
│   │   ├── CrawlMCPServer.ts    # MCP服务器
│   │   ├── CallOrchestrator.ts  # 调用编排器
│   │   └── StateManager.ts     # 状态管理
│   ├── adapters/          # 输出适配器
│   │   ├── MCPOutputAdapter.ts  # MCP格式转换
│   │   └── FileOutputAdapter.ts # 文件输出
│   ├── clients/           # 客户端
│   │   └── PlaywrightMCPClient.ts # Playwright客户端
│   ├── processors/        # 内容处理器
│   │   ├── ContentExtractor.ts  # 内容提取
│   │   ├── MarkdownConverter.ts # Markdown转换
│   │   └── ImageProcessor.ts    # 图片处理
│   ├── tools/             # MCP工具定义
│   ├── types/             # TypeScript类型
│   └── utils/             # 工具函数
├── docs/                  # 文档
├── examples/              # 示例代码
└── tests/                 # 测试文件

🧪 开发和测试

安装依赖

pnpm install

构建项目

pnpm build

运行测试

pnpm test

本地开发

pnpm dev

📊 测试覆盖

✅ **25

... View full README on GitHub

Loading README…

Scored, not listed

Why this score

Five weighted categories — click any category to see the underlying evidence.

Score breakdown

49/100across 5 weighted dimensions

How we score →

0255075100

−51

Security

Maintenance

Efficiency

Documentation

Compatibility

Categoriesclick a row to see evidence

Security

OSV.dev

No known CVEs.

Checked crawl-mcp-server against OSV.dev.

Community

Reviews

Be the first to review

Have you used this server?

Share your experience — it helps other developers decide.

How easy was setup?Did it work reliably?How was the documentation?

Frequently Asked Questions

Is Crawl Mcp safe to use?: Crawl Mcp has no known CVEs as of the latest MCPpedia security scan. It does not require authentication, so any local process can connect — keep this in mind in shared environments. Licensed under MIT.
How do I install Crawl Mcp?: Crawl Mcp supports copy-paste install configs on its MCPpedia page for Claude Desktop, Cursor, and Claude Code. Scroll to the Quick Install section and select your client.
What AI clients work with Crawl Mcp?: Crawl Mcp is compatible with claude-desktop, cursor, claude-code. It uses stdio and http transport.
Is Crawl Mcp actively maintained?: Crawl Mcp is less actively maintained — last commit was 345 days ago. It has 38 GitHub stars.