FastMCP Todo Server

Name: FastMCP Todo Server
Author: DanEdens

@DanEdens

FastMCP Todo Server について

A comprehensive MCP-based todo management system, that serves as a central nervous system for Madness Interactive, a multi-project task coordination workshop.

#mcp-server

基本情報

カテゴリ

生産性

ランタイム

python

トランスポート

stdio

公開者

DanEdens

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": {
    "Omnispindle": {
      "command": "python",
      "args": [
        "-m",
        "src.Omnispindle.stdio_server"
      ]
    }
  }
}

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 Omnispindle?

Omnispindle is a Python FastMCP server with 38 tools that lets AI agents manage tasks, capture knowledge, coordinate sessions, track epic goals (quests), and navigate a multi‑project development ecosystem from a single MCP interface. It integrates with Auth0 for zero‑config authentication and runs anywhere an MCP configuration lives.

How to use Omnispindle?

Install via pip install omnispindle, then run omnispindle-stdio for Claude Desktop or omnispindle-server for HTTP. Configure via environment variables (OMNISPINDLE_MODE, OMNISPINDLE_TOOL_LOADOUT, MCP_USER_EMAIL, etc.) and add the stdio command to claude_desktop_config.json for instant use. No manual token setup is required—the first tool call opens a browser for Auth0 login.

Key features of Omnispindle

38 MCP tools across 7 categories
Todo CRUD with dependencies, priority, and audit logging
Persistent knowledge capture with vector‑embedding semantic search
AI work session tracking with full genealogy trees
Quest system for multi‑step epic goals
Zero‑config Auth0 device‑flow authentication
Configurable tool loadouts to control agent token budget
Multiple operation modes: api, hybrid, local, auto

Use cases of Omnispindle

AI agents managing project tasks across teams
Capturing and retrieving lessons learned across sessions
Coordinating multi‑step objectives with dependency tracking
Providing agents a full project context bundle before starting work
Enabling cross‑agent communication via shared journals and knowledge cards

FAQ from Omnispindle

How does authentication work?

Omnispindle uses Auth0 device flow. On the first tool call, a browser opens for login; the token is saved locally and all subsequent calls are authenticated automatically. Manual token setup is optional via MCP_USER_EMAIL and MADNESS_AUTH_TOKEN.

What operation modes are available?

Set via OMNISPINDLE_MODE: api (HTTP calls to madnessinteractive.cc), hybrid (API with MongoDB fallback, default), local (direct MongoDB connections), or auto (benchmarks and picks the faster one).

How do I control which tools the agent sees?

Use the OMNISPINDLE_TOOL_LOADOUT environment variable. Options include full (38 tools), basic (15), minimal (4), read_only (16), write_only (6), lessons (8), and others—each tailored to different use cases.

Is my data isolated from other users?

Yes. All data is scoped per user at the database level using the MCP_USER_EMAIL environment variable. Your todos, lessons, and sessions stay yours.

What are the runtime dependencies?

Omnispindle runs on Python and requires pip install. For local or hybrid modes, a MongoDB instance is needed. Real‑time events optionally use MQTT. Authentication relies on Auth0. No additional services are required for the default API mode.

「生産性」の他のコンテンツ

Todo List MCP Server

RegiByte

An MCP server for managing todos within LLMs, created for educational purposes

🚀 TaskMaster: Todoist MCP for Cursor AI

mingolladaniele

A lightweight Model Context Protocol (MCP) server that enables natural language interaction with your Todoist tasks directly from your IDE. Built with simplicity and maintainability in mind.