返回 MCP 目录
public公开dns本地运行

MCP Kibela服务

一种模型上下文协议服务器,使AI助手能够搜索和访问存储在Kibela中的信息,支持笔记的搜索、检索、创建和更新。

article

README

mcp-kibela 🗒️

smithery badge npm version License: MIT

A Model Context Protocol (MCP) server implementation that enables AI assistants to search and reference Kibela content. This setup allows AI models like Claude to securely access information stored in Kibela.

Features 🚀

The mcp-kibela server provides the following features:

  • Note Search: Search Kibela notes by keywords
  • My Notes: Fetch your latest notes
  • Note Content: Get note content and comments by ID
  • Note by Path: Get note content by path
  • Create Note: Create a new note
  • Update Note Content: Update note content by note id

Prerequisites 📋

Before you begin, ensure you have:

  • Node.js (v18 or higher)
  • MCP Client (Claude Desktop, Cursor, etc.)
  • Kibela Access Token (How to get a token)
  • Git (if building from source)

Installation 🛠️

Usage with Cursor

{
  "kibela": {
    "command": "docker",
    "args": [
      "run",
      "-i",
      "--rm",
      "-e",
      "KIBELA_TEAM",
      "-e",
      "KIBELA_TOKEN",
      "ghcr.io/kj455/mcp-kibela:latest"
    ],
    "env": {
      "KIBELA_TEAM": "your-team-name from https://[team-name].kibe.la",
      "KIBELA_TOKEN": "your-token"
    }
  }
}

Usage with VSCode

{
  "mcp": {
    "inputs": [
      {
        "type": "promptString",
        "id": "kibela_team",
        "description": "Kibela team name",
        "password": false
      },
      {
        "type": "promptString",
        "id": "kibela_token",
        "description": "Kibela token",
        "password": true
      },
    ],
    "servers": {
      "kibela": {
        "command": "docker",
        "args": [
          "run",
          "-i",
          "--rm",
          "-e",
          "KIBELA_TEAM",
          "-e",
          "KIBELA_TOKEN",
          "ghcr.io/kj455/mcp-kibela:latest"
        ],
        "env": {
          "KIBELA_TEAM": "${input:kibela_team}",
          "KIBELA_TOKEN": "${input:kibela_token}"
        }
      }
    }
  }
}

Usage with Claude Desktop

{
  "mcpServers": {
    "mcp-kibela": {
      "command": "docker",
      "args": [
        "run",
        "-i",
        "--rm",
        "-e",
        "KIBELA_TEAM",
        "-e",
        "KIBELA_TOKEN",
        "ghcr.io/kj455/mcp-kibela:latest"
      ],
      "env": {
        "KIBELA_TEAM": "your-team-name from https://[team-name].kibe.la",
        "KIBELA_TOKEN": "your-token"
      }
    }
  }
}

Using Smithery

npx -y @smithery/cli install @kj455/mcp-kibela --client claude

Environment Variables

The following environment variables are required:

  • KIBELA_TEAM: Your Kibela team name (required). You can find it from the URL of your Kibela team page. e.g. https://[team-name].kibe.la
  • KIBELA_TOKEN: Your Kibela API token (required)

Contributing

Any contributions are welcome!

Development

  1. Use npm run build:watch to build the project in watch mode.
npm run build:watch
  1. Use npx @modelcontextprotocol/inspector to inspect the MCP server.
npx @modelcontextprotocol/inspector node /path/to/mcp-kibela/dist/index.js

License 📄

MIT

help

运行方式说明

cloud

托管运行

托管运行通常表示这个 MCP Server 由服务方环境承载,用户一般按页面提供的连接方式或授权流程接入,不需要在本地长期启动一个 MCP 进程

  1. 打开服务方连接页
  2. 完成授权或复制端点
  3. 在 MCP 客户端中连接
terminal

本地运行 / 其它方式

本地运行通常需要用户在自己的电脑或服务器上安装依赖,把 server_config 复制到 MCP 客户端,并按 env_schema 补齐环境变量、密钥或其它配置

  1. 复制 server_config
  2. 安装所需依赖
  3. 补齐环境变量后重启客户端