Aas-ee / open-webSearch

Open-WebSearch MCP Server **🇨🇳 中文 | 🇺🇸 English** A Model Context Protocol (MCP) server based on multi-engine search results, supporting free web search without API keys. Features • Web search using multi-engine results • bing • baidu • ~~linux.do~~ temporarily unsupported • csdn • duckduckgo • exa • brave • juejin • HTTP proxy configuration support for accessing restricted resources • No API keys or authentication required • Returns structured results with titles, URLs, and descriptions • Configurable number of results per search • Customizable default search engine • Support for fetching individual article content • csdn • github (README files) • generic HTTP(S) page / Markdown content TODO • Support for ~~Bing~~ (already supported), ~~DuckDuckGo~~ (already supported), ~~Exa~~ (already supported), ~~Brave~~ (already supported), Google and other search engines • Support for more blogs, forums, and social platforms • Optimize article content extraction, add support for more sites • ~~Support for GitHub README fetching~~ (already supported) Installation Guide NPX Quick Start (Recommended) The fastest way to get started: **Environment Variables:** | Variable | Default | Options | Description | |----------|-------------------------|---------|-------------| | | | , | Enable CORS | | | | Any valid origin | CORS origin configuration | | | | , , , , , , | Default search engine | | | | , | Enable HTTP proxy | | | | Any valid URL | Proxy server URL | | | | , , | Server mode: both HTTP+STDIO, HTTP only, or STDIO only | | | | 1-65535 | Server port | | | empty (all available) | Comma-separated engine names | Limit which search engines can be used; if the default engine is not in this list, the first allowed engine becomes the default | | | | Valid MCP tool name | Custom name for the search tool | | | | Valid MCP tool name | Custom name for the Linux.do article fetch tool | | | | Valid MCP tool name | Custom name for the CSDN article fetch tool | | | | Valid MCP tool name | Custom name for the GitHub README fetch tool | | | | Valid MCP tool name | Custom name for the Juejin article fetch tool | | | | Valid MCP tool name | Custom name for generic web/Markdown fetch tool | **Common configurations:** Local Installation • Clone or download this repository • Install dependencies: • Build the server: • Add the server to your MCP configuration: **Cherry Studio:** **VSCode (Claude Dev Extension):** **Claude Desktop:** **NPX Command Line Configuration:** **Local STDIO Configuration for Cherry Studio (Windows):** Docker Deployment Quick deployment using Docker Compose: Or use Docker directly: Environment variable configuration: | Variable | Default | Options | Description | |----------|-------------------------|---------|-------------| | | | , | Enable CORS | | | | Any valid origin | CORS origin configuration | | | | , , , | Default search engine | | | | , | Enable HTTP proxy | | | | Any valid URL | Proxy server URL | | | | 1-65535 | Server port | Then configure in your MCP client: Usage Guide The server provides six tools: , , , , , and . search Tool Usage Usage example: Response example: fetchCsdnArticle Tool Usage Used to fetch complete content of CSDN blog articles. Usage example: Response example: fetchLinuxDoArticle Tool Usage Used to fetch complete content of Linux.do forum articles. Usage example: Response example: fetchGithubReadme Tool Usage Used to fetch README content from GitHub repositories. Usage example: Supported URL formats: • HTTPS: • HTTPS with .git: • SSH: • URLs with parameters: Response example: fetchWebContent Tool Usage Fetch content directly from public HTTP(S) links, including Markdown files ( ) and ordinary web pages. Usage example: Response example: fetchJuejinArticle Tool Usage Used to fetch complete content of Juejin articles. Usage example: Supported URL format: • Response example: Usage Limitations Since this tool works by scraping multi-engine search results, please note the following important limitations: • **Rate Limiting**: • Too many searches in a short time may cause the used engines to temporarily block requests • Recommendations: • Maintain reasonable search frequency • Use the limit parameter judiciously • Add delays between searches when necessary • **Result Accuracy**: • Depends on the HTML structure of corresponding engines, may fail when engines update • Some results may lack metadata like descriptions • Complex search operators may not work as expected • **Legal Terms**: • This tool is for personal use only • Please comply with the terms of service of corresponding engines • Implement appropriate rate limiting based on your actual use case • **Search Engine Configuration**: • Default search engine can be set via the environment variable • Supported engines: bing, duckduckgo, exa, brave • The default engine is used when searching specific websites • **Proxy Configuration**: • HTTP proxy can be configured when certain search engines are unavailable in specific regions • Enable proxy with environment variable • Configure proxy server address with Contributing Welcome to submit issue reports and feature improvement suggestions! Contributor Guide If you want to fork this repository and publish your own Docker image, you need to make the following configurations: GitHub Secrets Configuration To enable automatic Docker image building and publishing, please add the following secrets in your GitHub repository settings (Settings → Secrets and variables → Actions): **Required Secrets:** • : Automatically provided by GitHub (no setup needed) **Optional Secrets (for Alibaba Cloud ACR):** • : Your Alibaba Cloud Container Registry URL (e.g., ) • : Your Alibaba Cloud ACR username • : Your Alibaba Cloud ACR password • : Your image name in ACR (e.g., ) CI/CD Workflow The repository includes a GitHub Actions workflow ( ) that automatically: • **Trigger Conditions**: • Push to branch • Push version tags ( ) • Manual work…