What prerequisites are needed?
Bun 1.0 or higher, a running Couchbase cluster (Capella free tier is recommended), and an MCP client such as Claude Desktop.
@zx8086
基本信息
暂无概览
使用下面的配置,将此服务器添加到你的 MCP 客户端。
{
"mcpServers": {
"mcp-server-couchbase-zx8086": {
"command": "bun",
"args": [
"run",
"build"
]
}
}
}工具列表暂未提供
当前收录暂时没有可展示的工具列表,不代表服务没有工具。请查阅项目文档了解支持的能力。
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
Couchbase MCP Server (TypeScript/Bun Version) is an MCP server implementation that allows LLMs to directly interact with Couchbase clusters. It is a TypeScript/Bun implementation of the original Python MCP server, providing type safety and better developer experience. It is intended for developers who want to enable AI assistants to perform operations on Couchbase data.
Clone the repository, install dependencies with bun install, build with bun run build, and create a .env file with Couchbase credentials. Then configure an MCP client (e.g., Claude Desktop) with a JSON entry pointing to bun and the built script, passing environment variables for connection string, username, password, bucket name, and optionally READ_ONLY_QUERY_MODE. Run with bun run dev (development) or bun run start (production). For SSE transport, use bun run dev:sse or bun run start:sse.
Bun 1.0 or higher, a running Couchbase cluster (Capella free tier is recommended), and an MCP client such as Claude Desktop.
Yes. The server has a `READ_ONLY_QUERY_MODE` environment variable set to `true` by default, which disables SQL++ queries that change data or collection structure.
Credentials are provided via environment variables in the MCP client configuration (or `.env` file locally). No credentials are stored in the server itself.
Yes. Use the `--transport=sse` flag or the `dev:sse` / `start:sse` scripts. The server listens on port 8080 by default, configurable via `FASTMCP_PORT`.
No. This project is community-maintained and not officially supported. Support is provided via GitHub issues.
AI Agents & MCPs & AI Workflow Automation • (~400 MCP servers for AI agents) • AI Automation / AI Agent with MCPs • AI Workflows & AI Agents • MCPs for AI Agents

Request dedicated senior developers to work on your project, write job descriptions, and prep technical interviews — all without leaving your Claude chat. Just describe what you need, and Lemon.io MCP does the rest. 1–3
Hindsight: Agent Memory That Learns

Run advanced phishing, voice phishing, deepfake fraud simulations, and cybersecurity awareness training from your AI assistant.
This open-source curriculum introduces the fundamentals of Model Context Protocol (MCP) through real-world, cross-language examples in .NET, Java, TypeScript, JavaScript, Rust and Python. Designed for developers, it focuses on practical techniques for building modular, scalable,
评论