Retable MCP Server
Connects AI agents like Claude, Cursor, and Windsurf to Retable for seamless AI-assisted data management. Enables AI agents to manage and interact with Retable workspaces, tables, and data through natural language.
README
Retable MCP Server: AI-Assisted Data Management
Connect AI agents like Claude, Cursor and Windsurf to Retable. With this MCP server, AI agents can help manage your Retable data seamlessly.
Usage
To use the MCP server, you must first configure your client (e.g., Claude, Cursor and Windsurf). Most clients provide an option to add a new MCP server.
Cursor one-click installation
Usage for Claude Desktop
For Claude Desktop, You’ll need to edit the claude_desktop_config.json file, which can be found via:
Settings → Developer → Edit Config
Add the following configuration to the "mcpServers" section of your claude_desktop_config.json:
{
"mcpServers": {
"retable": {
"command": "npx",
"args": ["-y", "retable-mcp-server"],
"env": {
"RETABLE_API_KEY": "$RETABLE_API_KEY"
}
}
}
}
⚠️ Replace $RETABLE_API_KEY with your Retable API Key.
After the configuration, restart Claude Desktop and you will see the active Retable tools
Prerequisites & Development
Before getting started, make sure you have the following:
- Node.js (version 20.0.0 or later)
- A Retable account
- A Retable API Key
The project includes several npm scripts to help with development:
# Run TypeScript compiler in watch mode for development
npm run dev
# Build the project for production
npm run build
# Run ESLint on source files
npm run lint
# Automatically fix ESLint issues where possible
npm run lint:fix
# Test the MCP server locally with the inspector tool
npm run inspect
⚠️ To run npm run inspect, replace RETABLE_API_KEY to the inspect script.
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。