Synthetic Search MCP Server
Provides privacy-focused web search capabilities with zero-data-retention for MCP-enabled applications. It allows users to execute search queries and retrieve ranked results using the Synthetic Search API.
README
<div align="center">
🔍 Synthetic Search MCP Server
Web search capabilities for your MCP-enabled applications with zero-data-retention privacy.
Installation • Usage • Configuration • API Reference
</div>
✨ Features
<table> <tr> <td width="50%">
🔒 Privacy First
Zero-data-retention search ensures your queries remain private and secure.
</td> <td width="50%">
⚡ Fast & Accurate
Get relevant web search results in milliseconds with high-quality ranking.
</td> </tr> <tr> <td width="50%">
🔧 Easy Integration
Simple MCP tool interface that works seamlessly with OpenCode and other MCP clients.
</td> <td width="50%">
📦 Zero Dependencies
Lightweight implementation with minimal external dependencies for reliability.
</td> </tr> </table>
🚀 Installation
Prerequisites
- Node.js 20 or higher
- A Synthetic API key (Get one here)
Quick Start
# Clone the repository
git clone https://github.com/joephaser/synthetic-search-mcp.git
cd synthetic-search-mcp
# Install dependencies
npm install
# Build the project
npm run build
🎯 Usage
1. Configure Your API Key
# Option 1: Environment variable
export SYNTHETIC_API_KEY="your-api-key-here"
# Option 2: Using .env file
cp .env.example .env
# Edit .env and add your API key
2. Run the Server
# Production mode
npm start
# Development mode with hot reload
npm dev
3. Test It
export SYNTHETIC_API_KEY="your-api-key"
npm test
⚙️ Configuration
OpenCode Integration
Add this MCP server to your OpenCode configuration at ~/.config/opencode/opencode.json:
{
"$schema": "https://opencode.ai/config.json",
"mcp": {
"synthetic-search": {
"type": "local",
"command": ["node", "/path/to/synthetic-search-mcp/dist/index.js"],
"environment": {
"SYNTHETIC_API_KEY": "your-api-key-here"
},
"enabled": true
}
}
}
Note: Replace
/path/to/synthetic-search-mcpwith the actual path to your installation andyour-api-key-herewith your Synthetic API key.
📚 API Reference
Tool: synthetic_search
Search the web using Synthetic's privacy-focused search API.
Parameters
| Parameter | Type | Required | Description |
|---|---|---|---|
query |
string |
✅ Yes | The search query to execute |
Example Request
{
"query": "latest TypeScript features 2024"
}
Response Format
{
"results": [
{
"title": "What's New in TypeScript 5.4",
"url": "https://example.com/article",
"date": "2024-03-15",
"snippet": "TypeScript 5.4 introduces several exciting features..."
}
]
}
Result Fields
- Title - The page title
- URL - Direct link to the source
- Date - Publication date (when available)
- Snippet - Relevant excerpt from the content
🛠️ Development
# Run in development mode
npm run dev
# Build for production
npm run build
# Run linting
npm run lint
# Run tests
npm test
📄 License
This project is licensed under the MIT License - see the LICENSE file for details.
<div align="center">
Made with ❤️ for the MCP community
</div>
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。