MCP.so
登录

FastMCP Todo Server

@DanEdens

关于 FastMCP Todo Server

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

基本信息

分类

生产力

运行时

python

传输方式

stdio

发布者

DanEdens

配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

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

工具

未检测到工具

工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。

概览

What is FastMCP Todo Server?

FastMCP Todo Server is a Python FastMCP server providing 38 tools for AI agents to manage tasks, capture knowledge, coordinate sessions, track epic goals (quests), and access project context through a single standardized interface. It integrates with Auth0 for authentication and can run in API, hybrid, local, or auto operation modes. Designed for multi-project AI-assisted development labs.

How to use FastMCP Todo Server?

Install via pip install omnispindle. Run the stdio server (omnispindle-stdio) for Claude Desktop or the HTTP web server (omnispindle/omnispindle-server) for authenticated endpoints. Set environment variables like OMNISPINDLE_MODE, OMNISPINDLE_TOOL_LOADOUT, and MCP_USER_EMAIL. For Claude Desktop, add a JSON entry to claude_desktop_config.json with the command omnispindle-stdio and required environment variables.

Key features of FastMCP Todo Server

  • Todo management with full metadata, priority, target agent, and change detection
  • Knowledge capture with language, topic, tags, and semantic vector search
  • Session tracking with genealogy trees, forking, and spawning
  • Quest system for multi-step objectives with progress reports
  • Context bundles giving agents a full project picture in one call
  • Zero‑config Auth0 device flow authentication
  • Tool loadouts (full, basic, minimal, etc.) to control tool availability
  • Operation modes: API, hybrid, local, auto

Use cases of FastMCP Todo Server

  • AI agents creating, updating, and completing tasks across multiple projects
  • Capturing lessons learned and retrieving them via text or semantic similarity
  • Coordinating AI work

评论

生产力 分类下的更多 MCP 服务器