Back to MCP directory
publicPublicdnsLocal runtime

mcp-kibela

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

Runtime guide

cloud

Hosted runtime

Hosted servers run from a provider-managed environment. You usually connect the MCP client to the hosted endpoint or follow the provider's authorization flow, without keeping a local process alive

  1. Open provider connection page
  2. Authorize or copy endpoint
  3. Connect from your MCP client
terminal

Local runtime / other methods

Local servers run on your own machine or infrastructure. You normally copy the server_config into your MCP client, install the required package, and provide env variables from env_schema when needed

  1. Copy server_config
  2. Install required package
  3. Fill env variables and restart client