nudge
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TODOIST_API_KEY | No | API key for Todoist adapter. Set this environment variable to use Todoist as the backend. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
This server publishes no instructions, or was last inspected before Glama recorded them.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {} |
| prompts | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| check_tasksA | Check whether specific things have been done. Fuzzy-matches task names so you don't need exact wording. Great for friendly check-ins: 'did you ever call the dentist?' Use this when the user mentions something they said they'd do and you want to see if it's on the list and whether it's ticked off. |
| get_pending_todayA | See what's still on the user's plate for today — useful for a natural mid-day or end-of-day check-in. If it's getting late and there are still open tasks, that's worth a gentle mention. |
| list_todosB | List the user's tasks with optional filters. Use this when asked directly, or when you need context to give a useful, honest answer about where things stand. |
| get_statsA | Get an honest summary of where things stand: total tasks, done today, pending, overdue. Use this for an end-of-day check-in or when the user wants the big picture. |
| search_todosB | Search across task titles and notes by keyword. |
| create_todoA | Add a new task to the user's list. Use this when the user says something like 'remind me to...' or 'add X to my list' or 'I need to do Y by Friday'. Confirm what you added so they know it landed. |
| mark_completeA | Mark a task as done. Use this when the user says 'done', 'finished', 'crossed that off', or anything that means they completed something. Fuzzy-match the name first with check_tasks if you're not sure of the exact ID. Celebrate appropriately — one line is enough. |
| mark_incompleteA | Reopen a task that was marked done. Use when the user says something like 'actually I didn't finish that' or 'reopen X'. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
| nudge-persona | Suggested system prompt — gives the AI the 'friend nudge' personality |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 8 tools
Tools are mostly distinct but check_tasks and search_todos overlap in searching, and list_todos with filters overlaps with get_pending_today and get_stats, causing mild ambiguity.
All tool names follow a consistent verb_noun snake_case pattern (e.g., create_todo, mark_complete), making them predictable and easy to distinguish.
With 8 tools, the set is well-scoped for a task management assistant, covering core operations without being overwhelming.
The set covers CRUD operations except for task deletion, and lacks editing capabilities, but the core lifecycle (create, read, update status) is present.