FastMCP Todo Server MCP Server

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

Local serverstdioPython

What is the FastMCP Todo Server MCP server?

FastMCP Todo Server MCP server exists for a simple reason — assistants are far more useful when they can act on FastMCP Todo Server directly instead of describing what you should do. A comprehensive MCP-based todo management system, that serves as a central nervous system for Madness Interactive, a multi-project task coordination workshop.

What you get

Omnispindle is the coordination spine of the Madness Interactive ecosystem — a Python FastMCP server with 38 tools that lets AI agents manage tasks, capture knowledge, coordinate sessions, track epic goals (quests), and navigate the whole workshop from a single, standardized interface. PyPI packaged. Auth0 integrated. Runs anywhere a MCP config lives.

Setting it up

The server ships on npm as @madnessengineering/cartogomancy, so your MCP client can launch it on demand — there is no separate build step. Add the server block to your client's configuration, restart it, and the tools register themselves.

What the assistant can call

Once FastMCP Todo Server is connected, these are the calls the assistant has available:

  • add_todo — Create a task with project, priority, target agent, notes, and metadata
  • query_todos — MongoDB-style filter queries with projection, limit, offset, since change detection, and graph_root for dependency subgraph traversal
  • update_todo — Patch any fields; metadata is deep-merged. Supports $push/$pull on array fields (e.g. metadata.blockers) for dependency linking
  • delete_todo — Remove a task
  • get_todo — Fetch a single task by ID
  • complete_todo — Stage for review with optional comment; writes to audit log. Sets status to review, not completed
  • list_todos_by_status — Filter by status: pending initial in_progress blocked review completed
  • search_todos — Tokenized multi-word fuzzy text search
  • list_project_todos — Recent tasks for a specific project
  • add_lesson — Capture a lesson with language, topic, and tags
  • get_lesson — Fetch by ID
  • update_lesson — Patch lesson content or metadata

Configuration and credentials

You will need 7 environment variables: OMNISPINDLE_MODE, OMNISPINDLE_TOOL_LOADOUT, MCP_USER_EMAIL, MADNESS_AUTH_TOKEN, AUTH0_TOKEN, MADNESS_API_URL, MQTT_HOST. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

Before you rely on it

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • With 14 tools registered it takes up a noticeable share of the context window; turn it off in projects that never touch FastMCP Todo Server.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the fastmcp todo server mcp server does with a few real requests.

Choosing this one

This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. FastMCP Todo Server's toolset — add_todo, query_todos, update_todo and 11 more — is a fair guide to whether it matches your workflow. It is maintained by DanEdens; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against FastMCP Todo Server's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Available tools

ToolWhat it does
add_todoCreate a task with project, priority, target agent, notes, and metadata
query_todosMongoDB-style filter queries with projection, limit, offset, since change detection, and graph_root for dependency subgraph traversal
update_todoPatch any fields; metadata is deep-merged. Supports $push/$pull on array fields (e.g. metadata.blockers) for dependency linking
delete_todoRemove a task
get_todoFetch a single task by ID
complete_todoStage for review with optional comment; writes to audit log. Sets status to review, not completed
list_todos_by_statusFilter by status: pending initial in_progress blocked review completed
search_todosTokenized multi-word fuzzy text search
list_project_todosRecent tasks for a specific project
add_lessonCapture a lesson with language, topic, and tags
get_lessonFetch by ID
update_lessonPatch lesson content or metadata
delete_lessonRemove
search_lessonsText search across lesson fields

How to install the FastMCP Todo Server MCP server

{
  "mcpServers": {
    "fastmcp-todo-server": {
      "command": "npx",
      "args": ["-y", "@madnessengineering/cartogomancy"],
      "env": {
        "OMNISPINDLE_MODE": "your-value",
        "OMNISPINDLE_TOOL_LOADOUT": "your-value",
        "MCP_USER_EMAIL": "your-value",
        "MADNESS_AUTH_TOKEN": "your-value",
        "AUTH0_TOKEN": "your-value",
        "MADNESS_API_URL": "your-value",
        "MQTT_HOST": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OMNISPINDLE_MODEConfiguration value read at startup.Optional
OMNISPINDLE_TOOL_LOADOUTConfiguration value read at startup.Optional
MCP_USER_EMAILConfiguration value read at startup.Optional
MADNESS_AUTH_TOKENCredential the server authenticates with.Yes
AUTH0_TOKENCredential the server authenticates with.Yes
MADNESS_API_URLEndpoint or connection string the server talks to.Yes
MQTT_HOSTEndpoint or connection string the server talks to.Optional

Example prompts to try

  • Use FastMCP Todo Server to add todo.
  • Use FastMCP Todo Server to query todos.
  • Use FastMCP Todo Server to update todo.

Frequently asked questions

It connects FastMCP Todo Server to MCP-compatible AI assistants such as Claude and Cursor, exposing 14 tools (add_todo, query_todos, update_todo, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with FastMCP Todo Server directly.