Kibela MCP Server

Kibela MCP Server

MCP server for seamless LLM integration with Kibela knowledge management.

7
Stars
6
Forks
7
Watchers
1
Issues
Kibela MCP Server enables integration of Large Language Models (LLMs) with the Kibela note-sharing platform via the Model Context Protocol. It provides search, retrieval, and management of Kibela notes, users, groups, and folders, exposing these capabilities in a standardized MCP interface. The implementation utilizes Kibela's GraphQL API and supports configuration through environment variables and Docker. Designed for interoperability with tools like Cursor, it streamlines access and manipulation of organizational knowledge by AI systems.

Key Features

Search notes with advanced filters
Retrieve latest personal notes
Fetch content, comments, and attachments of notes
Manage groups and group folders
Like and unlike notes
List users and view permissions
Access recently viewed notes
Retrieve notes by specific paths
Supports both CLI and Docker deployment
Environment-based configuration

Use Cases

Integrating organizational knowledge into LLM-powered chatbots
Automating retrieval of up-to-date notes for AI systems
Enabling LLMs to manage and interact with groups and folders in Kibela
Facilitating contextual search and information extraction from Kibela
Providing LLMs with structured access to note comments and user metadata
Supporting AI-assisted content summarization or generation based on Kibela notes
Implementing knowledge-aware agents in enterprise environments
Automating onboarding by surfacing relevant documents to LLM assistants
Streamlining data access for knowledge workers via LLM interfaces
Powering advanced analytics on team knowledge repositories with AI

README

Kibela MCP Server

NPM Downloads License: MIT Trust Score smithery badge

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:

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

json
{
    "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:

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

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

and set environemtns

Docker

Build and run locally:

bash
docker build -t mcp-kibela-server .

Then use this configuration:

json
{
    "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

Star History

Star History Chart

Repository Owner

Repository Details

Language TypeScript
Default Branch main
Size 171 KB
Contributors 5
License MIT License
MCP Verified Nov 12, 2025

Programming Languages

TypeScript
94.94%
Dockerfile
3.04%
JavaScript
2.02%

Tags

Topics

kibela kibela-web-api mcp modelcontextprotocol

Join Our Newsletter

Stay updated with the latest AI tools, news, and offers by subscribing to our weekly newsletter.

We respect your privacy. Unsubscribe at any time.

Related MCPs

Discover similar Model Context Protocol servers

  • mcp-kibela

    mcp-kibela

    MCP server for secure, AI-assisted access to Kibela notes.

    mcp-kibela is a Model Context Protocol (MCP) server implementation that enables AI assistants to search, retrieve, create, and update content from Kibela, a team knowledge-sharing platform. It provides standardized endpoints for note search, fetching individual or recent notes, and managing note content. Integrating with tools like Claude, Cursor, and VSCode, it allows seamless, secure access to organizational knowledge through MCP-enabled clients. Authentication via environment variables ensures secure connections to Kibela APIs.

    • 12
    • MCP
    • kj455/mcp-kibela
  • HackMD MCP Server

    HackMD MCP Server

    MCP server connecting LLM clients to the HackMD collaborative note platform.

    HackMD MCP Server implements the Model Context Protocol (MCP) to provide a standardized interface between large language model (LLM) clients and the HackMD collaborative note service. Through HTTP and STDIO transports, it enables creation, retrieval, update, and deletion of notes, along with management of teams, user profiles, and history data. It supports deployment in both local and cloud environments, with secure API token-based authentication and configuration via environment variables or HTTP headers.

    • 43
    • MCP
    • yuna0x0/hackmd-mcp
  • Notion MCP Server

    Notion MCP Server

    Enable LLMs to interact with Notion using the Model Context Protocol.

    Notion MCP Server allows large language models to interface with Notion workspaces through a Model Context Protocol server, supporting both data retrieval and editing capabilities. It includes experimental Markdown conversion to optimize token usage for more efficient communication with LLMs. The server can be configured with environment variables and controlled for specific tool access. Integration with applications like Claude Desktop is supported for seamless automation.

    • 834
    • MCP
    • suekou/mcp-notion-server
  • kibitz

    kibitz

    The coding agent for professionals with MCP integration.

    kibitz is a coding agent that supports advanced AI collaboration by enabling seamless integration with Model Context Protocol (MCP) servers via WebSockets. It allows users to configure Anthropic API keys, system prompts, and custom context providers for each project, enhancing contextual understanding for coding tasks. The platform is designed for developers and professionals seeking tailored AI-driven coding workflows and provides flexible project-specific configuration.

    • 104
    • MCP
    • nick1udwig/kibitz
  • MyMCP Server (All-in-One Model Context Protocol)

    MyMCP Server (All-in-One Model Context Protocol)

    Powerful and extensible Model Context Protocol server with developer and productivity integrations.

    MyMCP Server is a robust Model Context Protocol (MCP) server implementation that integrates with services like GitLab, Jira, Confluence, YouTube, Google Workspace, and more. It provides AI-powered search, contextual tool execution, and workflow automation for development and productivity tasks. The system supports extensive configuration and enables selective activation of grouped toolsets for various environments. Installation and deployment are streamlined, with both automated and manual setup options available.

    • 93
    • MCP
    • nguyenvanduocit/all-in-one-model-context-protocol
  • MCP Manager for Claude Desktop

    MCP Manager for Claude Desktop

    A desktop app to manage Model Context Protocol (MCP) servers for Claude Desktop on MacOS.

    MCP Manager for Claude Desktop provides a user-friendly interface to manage Model Context Protocol (MCP) servers, enabling Claude to access private data, APIs, and local or remote services securely from a MacOS desktop. It facilitates rapid configuration and integration with a wide variety of MCP servers, including productivity tools, databases, and web APIs. The app runs locally to ensure data privacy and streamlines connecting Claude to new sources through simple environment and server settings management.

    • 270
    • MCP
    • zueai/mcp-manager
  • Didn't find tool you were looking for?

    Be as detailed as possible for better results