Mcp Kibela Server

What is Mcp Kibela Server about?

Mcp Kibela Server connects Large Language Models to Kibela, a collaborative knowledge‑base platform. It exposes Kibela functionality through a set of MCP tools, allowing automated agents to query notes, fetch content, manage groups/folders, like/unlike notes, and retrieve user information.

How to use Mcp Kibela Server?

1. Install the server via npm or Docker. The most convenient method is using npx:

   {
     "mcpServers": {
       "kibela": {
         "command": "npx",
         "args": ["-y", "@kiwamizamurai/mcp-kibela-server"],
         "env": {
           "KIBELA_TEAM": "YOUR_TEAM_NAME",
           "KIBELA_TOKEN": "YOUR_TOKEN"
         }
       }
     }
   }
   

2. Add the above configuration to ~/.cursor/mcp.json (or the appropriate MCP client config).
3. Ensure the environment variables KIBELA_TEAM and KIBELA_TOKEN are set with your Kibela team name and API token.
4. Invoke the provided tools (e.g., kibela_search_notes, kibela_get_note_content) from your LLM workflow or CLI.

Key features of Mcp Kibela Server

• Search notes with advanced filters (co‑editing, archived, sort options, user/folder constraints).
• Retrieve latest notes belonging to the authenticated user.
• Fetch full note content, including HTML, comments, attachments, and image data URLs.
• Group and folder management: list groups, retrieve folders, and get notes within groups or folders.
• User directory: obtain user IDs, account names, and real names.
• Interaction actions: like and unlike notes.
• Recent activity: list recently viewed notes.
• Path‑based lookup: get a note by its Kibela path or full URL.

Use cases of Mcp Kibela Server

• Automated knowledge retrieval for chat‑bots that need to reference internal documentation.
• Content summarization where an LLM aggregates multiple Kibela notes into a concise report.
• Workflow automation such as automatically tagging or moving notes based on AI analysis.
• Personal productivity assistants that fetch a user's latest notes or recent activity.
• Team collaboration tools that surface relevant group/folder notes during meetings.

FAQ from the Mcp Kibela Server

• Do I need a Kibela account? Yes, a valid team name and API token are required.
• Can I run the server locally? Yes, clone the repo, run npm install, and execute the built index with Node or use the provided Docker image.
• What transport does the server use? It supports standard MCP HTTP as well as Server‑Sent Events (SSE) when running via Docker (http://localhost:3000/sse).
• How are images handled in note content? Set include_image_data to true to embed image data URLs; otherwise only URLs are returned.
• Is there a limit on fetched notes? Most list operations have default limits (e.g., 15 for recent notes, up to 100 for folder notes) which can be overridden via the limit parameter.

Kibela MCP Server

MCP server implementation for Kibela API integration, enabling LLMs to interact with Kibela content.

[!TIP] This extension performs GraphQL schema introspection using the buildClientSchema, getIntrospectionQuery, and printSchema functions from the graphql package to reverse engineer Kibela's API. For more details, see her

Features

• Search notes with advanced filters
• Get your latest notes
• Get note content and comments
• Manage groups and folders
• Like/unlike notes
• List users
• View note attachments
• View recently viewed notes
• Get notes by path

Configuration

Environment Variables

• KIBELA_TEAM: Your Kibela team name (required)
• KIBELA_TOKEN: Your Kibela API token (required)

Cursor Integration

Add to your ~/.cursor/mcp.json:

{
    "mcpServers": {
        "kibela": {
            "command": "npx",
            "args": ["-y", "@kiwamizamurai/mcp-kibela-server"],
            "env": {
                "KIBELA_TEAM": "YOUR_TEAM_NAME",
                "KIBELA_TOKEN": "YOUR_TOKEN"
            }
        }
    }
}

If you want to use docker instead

{
    "mcpServers": {
        "kibela": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "KIBELA_TEAM",
                "-e",
                "KIBELA_TOKEN",
                "ghcr.io/kiwamizamurai/mcp-kibela-server:latest"
            ],
            "env": {
                "KIBELA_TEAM": "YOUR_TEAM_NAME",
                "KIBELA_TOKEN": "YOUR_TOKEN"
            }
        }
    }
}

Tools

kibela_search_notes

Search Kibela notes with given query

• Input:
  • query (string): Search query
  • coediting (boolean, optional): Filter by co-editing status
  • isArchived (boolean, optional): Filter by archive status
  • sortBy (string, optional): Sort by (RELEVANT, CONTENT_UPDATED_AT)
  • userIds (string[], optional): Filter by user IDs
  • folderIds (string[], optional): Filter by folder IDs
• Returns: List of matching notes with ID, title, URL, author, groups and more

kibela_get_my_notes

Get your latest notes from Kibela

• Input:
  • limit (number, optional): Number of notes to fetch (default: 15)
• Returns: List of your latest notes with author information

kibela_get_note_content

Get content and comments of a specific note

• Input:
  • id (string): Note ID
  • include_image_data (boolean, optional): Whether to include image data URLs in the response (default: false)
• Returns: Full note content including HTML, comments, attachments, groups, folders and more

kibela_get_groups

Get list of accessible groups

• Input: None
• Returns: List of groups with details like privacy settings and permissions

kibela_get_group_folders

Get folders in a group

• Input:
  • groupId (string): Group ID
  • parentFolderId (string, optional): Parent folder ID for nested folders
• Returns: List of folders with their notes and metadata

kibela_get_group_notes

Get notes in a group that are not attached to any folder

• Input:
  • groupId (string): Group ID
• Returns: List of notes with author information, sorted by last update time

kibela_get_folder_notes

Get notes in a folder

• Input:
  • folderId (string): Folder ID
  • limit (number, optional): Number of notes to fetch (default: 100)
• Returns: List of notes with author information, sorted by last update time

kibela_get_users

Get list of users

• Input: None
• Returns: List of users with ID, account and real name

kibela_like_note

Like a note

• Input:
  • noteId (string): Note ID
• Returns: Updated likers list

kibela_unlike_note

Unlike a note

• Input:
  • noteId (string): Note ID
• Returns: Updated likers list

kibela_get_recently_viewed_notes

Get your recently viewed notes

• Input:
  • limit (number, optional): Number of notes to fetch (max 15)
• Returns: List of recently viewed notes with author information

kibela_get_note_from_path

Get note content by its path or URL

• Input:
  • path (string): Note path (e.g. '/group/folder/note') or full Kibela URL (e.g. 'https://team.kibe.la/notes/123')
  • include_image_data (boolean, optional): Whether to include image data URLs in the response (default: false)
• Returns: Full note content including HTML, comments, attachments, groups, folders and more

Local Development

Running from Source

1. Clone the repository
2. Install dependencies: npm install

Environment Setup

For local development, update your ~/.cursor/mcp.json:

{
    "mcpServers": {
        "kibela": {
            "command": "node",
            "args": ["path/to/mcp-kibela-server/dist/src/index.js"],
            "env": {
                "KIBELA_TEAM": "YOUR_TEAM_NAME",
                "KIBELA_TOKEN": "YOUR_TOKEN"
            }
        }
    }
}

MCP inspector

npx @modelcontextprotocol/inspector node ./dist/src/index.js

and set environemtns

Docker

Build and run locally:

docker build -t mcp-kibela-server .

Then use this configuration:

{
    "mcpServers": {
        "kibela": {
            "command": "docker",
            "args": [
                "run",
                "-i",
                "--rm",
                "-e",
                "KIBELA_TEAM",
                "-e",
                "KIBELA_TOKEN",
                "mcp-kibela-server"
            ],
            "env": {
                "KIBELA_TEAM": "YOUR_TEAM_NAME",
                "KIBELA_TOKEN": "YOUR_TOKEN"
            }
        }
    }
}

For SSE transport, ensure the server URL is set to: http://localhost:3000/sse

Other products

• vscode extension for kibela