mcp-kibela
by: kj455
MCP server implementation that enables AI assistants to search and reference Kibela content
๐Overview
Purpose: To provide a server implementation that enables AI assistants to securely search and reference content stored in Kibela.
Overview: The mcp-kibela server facilitates communication between AI models and Kibela, allowing users to access, manage, and retrieve notes efficiently within their AI-driven applications.
Key Features:
-
Note Search: Allows users to search for Kibela notes using keywords, enabling efficient information retrieval.
-
My Notes: Provides the ability to fetch the latest notes authored by the user, streamlining access to recent information.
-
Note Content: Retrieves content and comments for a specific note based on its ID, facilitating detailed content review.
-
Note by Path: Enables access to note content via its path, enhancing navigation through structured note hierarchies.
-
Create Note: Allows users to create new notes directly through the API, supporting content generation.
-
Update Note Content: Facilitates updating existing note content using the note ID, ensuring information stays current and relevant.
mcp-kibela ๐๏ธ
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 ๐
- 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 ๐
Before you begin, ensure you have:
- Node.js (v18 or higher)
- MCP Client (Claude Desktop, Cursor, etc.)
- Kibela Access Token (see: https://support.kibe.la/hc/ja/articles/360036089931-API%E3%82%A2%E3%82%AF%E3%82%BB%E3%82%B9%E3%83%88%E3%83%BC%E3%82%AF%E3%83%B3%E3%81%AE%E5%8F%96%E5%BE%97%E6%96%B9%E6%B3%95%E3%82%92%E6%95%99%E3%81%88%E3%81%A6%E3%81%8F%E3%81%A0%E3%81%95%E3%81%84)
- Git (if building from source)
Installation ๐ ๏ธ
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
KIBELA_TEAM
: Your Kibela team name (required). Find it from the URL of your Kibela team page, e.g. https://[team-name].kibe.laKIBELA_TOKEN
: Your Kibela API token (required)
Development
- Use
npm run build:watch
to build the project in watch mode.
npm run build:watch
- Use
npx @modelcontextprotocol/inspector
to inspect the MCP server.
npx @modelcontextprotocol/inspector node /path/to/mcp-kibela/dist/index.js
Contributing
Contributions are welcome!
License ๐
MIT