MCP.so
ログイン

Konbu

@krtw00

リポジトリ

Konbu について

A self-hostable all-in-one planner combining calendar, notes, todos, and bookmarks. Built-in MCP server lets Claude Desktop, Cursor, and any MCP client operate your personal data via natural language. Single Go binary, MIT licensed.

#planner#calendar#todos#notes#bookmarks#self-hosted#golang#productivity#pim#all-in-one

基本情報

カテゴリ

生産性

トランスポート

stdio

公開者

krtw00

投稿者

井口皓斗（クロトワ）

設定

以下の設定を使って、このサーバーを MCP 対応クライアントに追加してください。

{
  "mcpServers": {
    "konbu": {
      "command": "konbu",
      "args": [
        "mcp"
      ],
      "env": {
        "KONBU_API": "http://localhost:8080",
        "KONBU_API_KEY": "your-api-key"
      }
    }
  }
}

ツール

ツールは検出されませんでした

ツールは README から自動的に抽出されます。メンテナーは ## Tools という見出しの下に記載することで、このタブに反映できます。

概要

What is Konbu?

Konbu is a self-hostable digital planner that combines Notion, Todoist, and Google Calendar into a single Go binary. It includes a native MCP server that lets AI agents like Claude Desktop and Cursor read and write your data directly.

How to use Konbu?

After running a Konbu API server (self-hosted or using the cloud version), add the provided JSON configuration to your MCP client’s mcpServers block. The KONBU_API environment variable points to the server URL, and KONBU_API_KEY must be generated from the web UI’s Settings > Security.

Key features of Konbu

  • Native MCP server for natural language task management.
  • CLI client with commands like konbu memo add and konbu todo list.
  • Bring your own OpenAI/Anthropic API key or use the free tier.
  • Cross-resource full-text search across memos, todos, events, and bookmarks.
  • Self-hostable with Docker or use the hosted version at konbu-cloud.codenica.dev.
  • Supports calendar, Markdown notes, todos, bookmarks, AI chat, and export/import.

Use cases of Konbu

  • Schedule a dentist appointment by speaking naturally to an AI agent.
  • Manage all tasks, notes, and events from a terminal using the CLI.
  • Search across multiple resource types (memos, todos, events) in one query.
  • Run a fully offline planner on your own server with PostgreSQL.

FAQ from Konbu

What exactly does Konbu do?

It is an all-in-one digital planner that merges calendar, notes, todos, and bookmarks, and exposes them via an MCP server for AI agents.

How do I set up the MCP server?

After running a Konbu API server, add the JSON block shown in the README to your MCP client config, setting KONBU_API and KONBU_API_KEY. Generate the API key in Settings > Security on the web UI.

What are the runtime requirements?

Konbu is a single Go binary. It uses PostgreSQL as its database. You can run it with Docker for self-hosting.

Can I use Konbu without hosting my own server?

Yes, there is a hosted version available at konbu-cloud.codenica.dev.

How does authentication work for the MCP server?

The MCP server requires an API key passed via the KONBU_API_KEY environment variable. The key is generated from the web UI’s Settings > Security.

コメント

「生産性」の他のコンテンツ

Todoist MCP Server

greirson

MCP server that connects Claude to Todoist for natural language task and project management with bulk operations

245

🚀 Time MCP Server: Giving LLMs Time Awareness Capabilities

yokingma

⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities

67

MCP Shrimp Task Manager

cjo4m06

Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning A

2.1K

ATLAS: Task Management System

cyanheads

A Model Context Protocol (MCP) server for ATLAS, a Neo4j-powered task management system for LLM Agents - implementing a three-tier architecture (Projects, Tasks, Knowledge) to manage complex workflows. Now with Deep Research.

475

MCP Google Calendar Server

markelaugust74

A Model Context Protocol (MCP) server implementation for Google Calendar integration. Create and manage calendar events directly through Claude or other AI assistants.

32