Kibela Integration MCP Server

Knowledge & MemoryTypeScript

Search and reference Kibela content from AI assistants

Available Tools

searchNotes

Search Kibela notes by keywords

querylimit

getMyNotes

Fetch your latest notes

limit

getNoteContent

Get note content and comments by ID

noteId

getNoteByPath

Get note content by path

path

createNote

Create a new note

titlecontentgroupIdcoediting

updateNoteContent

Update note content by note id

noteIdcontent

The Kibela Integration MCP enables AI assistants to securely access, search, and reference information stored in Kibela knowledge bases. This integration allows AI models like Claude to retrieve notes, create new content, and update existing documents within your team's Kibela workspace. With this MCP, you can leverage your organization's knowledge base directly in AI conversations, making it easier to reference internal documentation, share information, and collaborate on content creation without leaving your AI assistant interface.

Overview

The Kibela Integration MCP connects your AI assistants to your Kibela knowledge base, allowing them to search, retrieve, create, and update content. This integration is particularly useful for teams that use Kibela as their internal knowledge management system and want to access that information directly through AI assistants.

Prerequisites

Before setting up the Kibela Integration MCP, you'll need:

Node.js v18 or higher (if building from source)
A Kibela account with API access
Your Kibela team name (found in your Kibela URL: https://[team-name].kibe.la)
A Kibela API access token (instructions for obtaining one are available in the Kibela support documentation)
An MCP-compatible client (Claude Desktop, Cursor, VSCode, etc.)

Installation Options

Using Docker (Recommended)

The simplest way to use this MCP is with the pre-built Docker image. You'll need to configure your AI client with the appropriate settings based on which client you're using.

Using Smithery

If you prefer using Smithery for installation:

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

Building from Source

If you want to build from source:

Clone the repository: git clone https://github.com/kj455/mcp-kibela.git
Install dependencies: npm install
Build the project: npm run build
Run the server: node dist/index.js

Configuration

The MCP requires two environment variables:

KIBELA_TEAM: Your Kibela team name (from your Kibela URL: https://[team-name].kibe.la)
KIBELA_TOKEN: Your Kibela API access token

Client Configuration

Claude Desktop

Add the following to your Claude Desktop configuration:

{
  "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",
        "KIBELA_TOKEN": "your-token"
      }
    }
  }
}

Cursor

Add the following to your Cursor configuration:

{
  "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",
      "KIBELA_TOKEN": "your-token"
    }
  }
}

VSCode

For VSCode, you can use input prompts to securely enter your credentials:

{
  "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

Once configured, your AI assistant can interact with your Kibela knowledge base. You can ask it to:

Search for notes on specific topics
Retrieve your latest notes
Get the content of a specific note by ID or path
Create new notes
Update existing notes

Simply ask your AI assistant to perform these actions in natural language, and it will use the appropriate tools to interact with Kibela.