Crawleo MCP

io.github.Crawleo由 GitHub 帳號 Crawleo 發布v1.0.0更新於 Oct 24, 2026

Hosted Crawleo MCP (remote streamable HTTP endpoint).

已驗證Streamable HTTP可網頁執行網頁搜尋與抓取瀏覽器自動化

概覽

AI 產生的概覽

託管式 Crawleo MCP 伺服器，讓助理進行即時網頁搜尋與網址擷取，可輸出 Markdown、HTML、純文字或截圖。

可以做什麼
  • 即時搜尋網頁，可設定結果頁數、語言、國家、裝置類型與輸出格式
  • 擷取一個或多個網址並取出內容，支援 Markdown、原始 HTML、純文字，可選擇截圖
  • 可選擇自動擷取搜尋結果中的連結，並同時回傳多種格式
適用情境
適合需要最新網路資訊而非模型訓練資料的情境：研究整理、新聞監控、競品與價格調查，以及從指定頁面取出文件或文章內容。
執行需求
使用 api.crawleo.dev 的遠端 streamable HTTP 端點，或透過 npx、Node.js 執行本機 npm 套件 crawleo-mcp，或使用 Docker 映像。需要 Crawleo 帳號與 API 金鑰，以 Authorization bearer 權杖傳送（本機執行時為 CRAWLEO_API_KEY）。需要網路連線。
安裝前請注意
API 金鑰是付費憑證，請勿寫入共用設定或對話中。依搜尋次數計費，README 列出付費方案，大量自動擷取會產生費用。搜尋字詞與擷取網址會傳送給第三方服務，其聲稱不保留資料。擷取會依助理要求存取任意網址。

安裝

在 SourceWeft 中

  1. 開啟 儀表板中的 Crawleo MCP，將其新增到工作區。
  2. 連接 Authorization token 憑證。它們會被私密儲存，絕不會在公開頁面上展示。
  3. 為需要使用其工具的對話啟用該服務。

Web executable，透過 Streamable HTTP。 遠端服務在工作區中設定後即可從網頁執行環境執行。

交給代理程式安裝

把這段提示詞貼上到 Claude Code、Codex、Cursor 等代理程式，或 SourceWeft 對話中。代理程式會讀取該伺服器的安裝指南，先向你展示發布者、端點和登入方式，經你同意後再把它新增到你的客戶端。金鑰不會寫進任何命令。

閱讀 https://sourceweft.com/mcp/io.github.Crawleo%2FCrawleo-MCP/install.md，並按其中說明把這個 MCP 伺服器接入我的客戶端。修改任何設定之前，先告訴我它的發布者、端點和登入方式，等我確認。不要把 API 金鑰寫進命令或我會提交的檔案；問我金鑰應從哪裡取得。

檢視代理程式所依據的安裝指南

其他 MCP 客戶端

把它新增到你客戶端的 mcpServers 設定中。

{
  "mcpServers": {
    "crawleo": {
      "type": "http",
      "url": "https://api.crawleo.dev/mcp",
      "headers": {
        "Authorization": "Bearer <YOUR_TOKEN>"
      }
    }
  }
}

README

Crawleo MCP Server

[Crawleo MCP server]

[smithery badge]

Real-time web search and crawling capabilities for AI assistants through Model Context Protocol (MCP).

Overview

Crawleo MCP enables AI assistants to access live web data through two powerful tools:

  • web.search - Real-time web search with multiple output formats
  • web.crawl - Deep content extraction from any URL

Features

✅ Real-time web search from any country/language
✅ Multiple output formats - Enhanced HTML, Raw HTML, Markdown, Plain Text
✅ Device-specific results - Desktop, mobile, or tablet view
✅ Deep content extraction with JavaScript rendering
✅ Zero data retention - Complete privacy
✅ Auto-crawling option for search results

Installation

Option 1: NPM (Recommended for local usage)

Install globally via npm:

bash
npm install -g crawleo-mcp

Or use npx without installing:

bash
npx crawleo-mcp

Option 2: Clone Repository

bash
git clone https://github.com/Crawleo/Crawleo-MCP.gitcd Crawleo-MCPnpm installnpm run build

Option 3: Docker

Build and run using Docker:

bash
# Build the imagedocker build -t crawleo-mcp .
# Run with your API keydocker run -e CRAWLEO_API_KEY=your_api_key crawleo-mcp

Docker configuration for MCP clients:

json
{  "mcpServers": {    "crawleo": {      "command": "docker",      "args": ["run", "-i", "--rm", "-e", "CRAWLEO_API_KEY=YOUR_API_KEY_HERE", "crawleo-mcp"]    }  }}

Option 4: Remote Server (No installation needed)

Use the hosted version at https://api.crawleo.dev/mcp - see configuration examples below.

Getting Your API Key

  1. Visit crawleo.dev
  2. Sign up for a free account
  3. Navigate to your dashboard
  4. Copy your API key (starts with sk_)

Setup Instructions

Using Local MCP Server (npm package)

After installing via npm, configure your MCP client to use the local server:

Claude Desktop / Cursor / Windsurf (Local):

json
{  "mcpServers": {    "crawleo": {      "command": "npx",      "args": ["crawleo-mcp"],      "env": {        "CRAWLEO_API_KEY": "YOUR_API_KEY_HERE"      }    }  }}

Or if installed globally:

json
{  "mcpServers": {    "crawleo": {      "command": "crawleo-mcp",      "env": {        "CRAWLEO_API_KEY": "YOUR_API_KEY_HERE"      }    }  }}

From cloned repository:

json
{  "mcpServers": {    "crawleo": {      "command": "node",      "args": ["/path/to/Crawleo-MCP/dist/index.js"],      "env": {        "CRAWLEO_API_KEY": "YOUR_API_KEY_HERE"      }    }  }}

Using Remote Server (Hosted)

1. Claude Desktop

Location of config file:

  • macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
  • Windows: %APPDATA%\Claude\claude_desktop_config.json
  • Linux: ~/.config/Claude/claude_desktop_config.json

Configuration:

json
{  "mcpServers": {    "crawleo": {      "url": "https://api.crawleo.dev/mcp",      "transport": "http",      "headers": {        "Authorization": "Bearer YOUR_API_KEY_HERE"      }    }  }}

Replace YOUR_API_KEY_HERE with your actual API key from crawleo.dev.

Steps:

  1. Open the config file in a text editor
  2. Add the Crawleo MCP configuration
  3. Save the file
  4. Restart Claude Desktop completely (quit and reopen)
  5. Start a new conversation and ask Claude to search the web!

Example usage:

"Search for the latest AI news and summarize the top 5 articles""Find Python web scraping tutorials and extract code examples"

2. Cursor IDE

Location of config file:

  • macOS: ~/.cursor/config.json or ~/Library/Application Support/Cursor/config.json
  • Windows: %APPDATA%\Cursor\config.json
  • Linux: ~/.config/Cursor/config.json

Configuration:

json
{  "mcpServers": {    "crawleo": {      "url": "https://api.crawleo.dev/mcp",      "transport": "http",      "headers": {        "Authorization": "Bearer YOUR_API_KEY_HERE"      }    }  }}

Steps:

  1. Locate and open your Cursor config file
  2. Add the Crawleo MCP configuration
  3. Save the file
  4. Restart Cursor
  5. The MCP tools will be available in your AI assistant

Example usage in Cursor:

"Search for React best practices and add them to my code comments""Find the latest documentation for this API endpoint"

3. Windsurf IDE

Location of config file:

  • macOS: ~/Library/Application Support/Windsurf/config.json
  • Windows: %APPDATA%\Windsurf\config.json
  • Linux: ~/.config/Windsurf/config.json

Configuration:

json
{  "mcpServers": {    "crawleo": {      "url": "https://api.crawleo.dev/mcp",      "transport": "http",      "headers": {        "Authorization": "Bearer YOUR_API_KEY_HERE"      }    }  }}

Steps:

  1. Open the Windsurf config file
  2. Add the Crawleo MCP server configuration
  3. Save and restart Windsurf
  4. Start using web search in your coding workflow

4. GitHub Copilot

Location of config file:

For GitHub Copilot in VS Code or compatible editors, you need to configure MCP servers.

Configuration:

Create or edit your MCP config file and add:

json
{  "servers": {    "Crawleo": {      "url": "https://api.crawleo.dev/mcp",      "transport": "http",      "headers": {        "Authorization": "Bearer YOUR_API_KEY_HERE"      }    }  }}

Complete example with multiple servers:

json
{  "servers": {    "Crawleo": {      "url": "https://api.crawleo.dev/mcp",      "transport": "http",      "headers": {        "Authorization": "Bearer YOUR_API_KEY_HERE"      }    }  }}

Steps:

  1. Open your GitHub Copilot MCP configuration
  2. Add the Crawleo server configuration
  3. Save the file
  4. Restart VS Code or your IDE
  5. GitHub Copilot can now use Crawleo for web searches!

Example usage:

Ask Copilot: "Search for the latest Python best practices"Ask Copilot: "Find documentation for this library"

5. OpenAI Platform (Direct Integration)

OpenAI now supports MCP servers directly! Here's how to use Crawleo with OpenAI's API:

Python Example:

python
from openai import OpenAI
client = OpenAI()
response = client.responses.create(    model="gpt-4",    input=[        {            "role": "user",            "content": [                {                    "type": "input_text",                    "text": "search for latest news about openai models"                }            ]        }    ],    text={        "format": {            "type": "text"        },        "verbosity": "medium"    },    reasoning={        "effort": "medium"    },    tools=[        {            "type": "mcp",            "server_label": "Crawleo",            "server_url": "https://api.crawleo.dev/mcp",            "server_description": "Crawleo MCP Server - Real-Time Web Knowledge for AI",            "authorization": "YOUR_API_KEY_HERE",            "allowed_tools": [                "web.search",                "web.crawl"            ],            "require_approval": "always"        }    ],    store=True,    include=[        "reasoning.encrypted_content",        "web_search_call.action.sources"    ])
print(response)

Key Parameters:

  • server_url - Crawleo MCP endpoint
  • authorization - Your Crawleo API key
  • allowed_tools - Enable web.search and/or web.crawl
  • require_approval - Set to "always", "never", or "conditional"

Node.js Example:

javascript
import OpenAI from 'openai';
const client = new OpenAI();
const response = await client.responses.create({  model: 'gpt-4',  input: [    {      role: 'user',      content: [        {          type: 'input_text',          text: 'search for latest AI developments'        }      ]    }  ],  tools: [    {      type: 'mcp',      server_label: 'Crawleo',      server_url: 'https://api.crawleo.dev/mcp',      server_description: 'Crawleo MCP Server - Real-Time Web Knowledge for AI',      authorization: 'YOUR_API_KEY_HERE',      allowed_tools: ['web.search', 'web.crawl'],      require_approval: 'always'    }  ]});
console.log(response);

Available Tools

web.search

Search the web in real-time with customizable parameters.

Parameters:

  • query (required) - Search term
  • max_pages - Number of result pages (default: 1)
  • setLang - Language code (e.g., "en", "ar")
  • cc - Country code (e.g., "US", "EG")
  • device - Device type: "desktop", "mobile", "tablet" (default: "desktop")
  • enhanced_html - Get clean HTML (default: true)
  • raw_html - Get raw HTML (default: false)
  • markdown - Get Markdown format (default: true)
  • page_text - Get plain text (default: false)
  • auto_crawling - Auto-crawl result URLs (default: false)

Example:

Ask your AI: "Search for 'Python web scraping' and return results in Markdown"

web.crawl

Extract content from specific URLs.

Parameters:

  • urls (required) - List of URLs to crawl
  • rawHtml - Return raw HTML (default: false)
  • markdown - Convert to Markdown (default: false)
  • screenshot - Capture screenshot (optional)
  • country - Geographic location

Example:

Ask your AI: "Crawl https://example.com and extract the main content in Markdown"

Troubleshooting

MCP server not appearing

  1. Check config file location - Make sure you're editing the correct file
  2. Verify JSON syntax - Use a JSON validator to check for syntax errors
  3. Restart the application - Completely quit and reopen (not just reload)
  4. Check API key - Ensure your API key is valid and active at crawleo.dev

Authentication errors

  • Verify your API key is correct (should start with sk_)
  • Make sure the key is wrapped in quotes
  • Check that "Bearer " prefix is included in the Authorization header (for Claude/Cursor/Windsurf)
  • For OpenAI Platform, use the key directly in the authorization field
  • Confirm your account has available credits at crawleo.dev

No results returned

  • Check your internet connection
  • Verify the search query is not empty
  • Try a simpler search query first
  • Check API status at crawleo.dev

Tool names not recognized

Make sure you're using the correct tool names:

  • Use web.search (not search_web)
  • Use web.crawl (not crawl_web)

Usage Examples

Research Assistant

"Search for recent developments in quantum computing and summarize the key findings"

Content Analysis

"Search for competitor pricing pages and extract their pricing tiers"

Code Documentation

"Find the official documentation for FastAPI and extract the quickstart guide"

News Monitoring

"Search for today's news about artificial intelligence from US sources"

Market Research

"Search for customer reviews of iPhone 15 and analyze sentiment"

Pricing

Crawleo MCP uses the same affordable pricing as our API:

  • 10,000 searches → $20
  • 100,000 searches → $100
  • 250,000 searches → $200

Check your usage and manage your subscription at crawleo.dev

Privacy & Security

✅ Zero data retention - We never store your search queries or results
✅ Secure authentication - API keys transmitted over HTTPS
✅ No tracking - Your usage patterns remain private

Support

Links

Is this better? Would you like me to add anything else or create additional guides?

來源：README.md，提交 e39746a

工具

0
該伺服器需要 API 金鑰等憑證，因此 SourceWeft 無法在沒有憑證的情況下讀取其工具，也未收錄。

版本歷史

1
  1. v1.0.0最新Sep 16, 2026

評分

已滿足適用檢查項的 85%

該評分衡量此收錄條目的完整程度，依據註冊中心條目、端點與公開來源計算得出。它不是對伺服器本身的評價，也不表示伺服器安全或目前可用：可連通性是帶日期的檢查結果，評分也不包含安裝量或使用者評價。

  • 近 30 天內可連通必需25 分
  • 已宣告認證方式必需10 分
  • 已列出工具15 分

    請讓伺服器在無憑證時回應 tools/list，或發布可在沙箱中無憑證啟動的軟體包。

  • 描述必需15 分
  • 圖示10 分
  • 文件15 分
  • 授權條款10 分