super-productivity-mcp
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| SP_API_URL | No | HTTP(S) URL; loopback is enforced by default | http://127.0.0.1:3876 |
| SP_API_TOKEN | No | Optional Bearer token for an authenticated Super Productivity build | |
| SP_LOG_LEVEL | No | error, warn, info, or debug | warn |
| SP_API_TIMEOUT_MS | No | Integer from 1000 to 60000 | 15000 |
| SP_ALLOW_NON_LOOPBACK_URL | No | Use only for a trusted local proxy | false |
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 | {
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| healthB | Check whether the local Super Productivity desktop API is reachable and ready. |
| check_connectionA | Check whether the local Super Productivity desktop API is reachable and ready. |
| search_tasksA | Find tasks by title or project. Returns task IDs for explicit follow-up actions. |
| list_todayA | List tasks explicitly planned for Today in Super Productivity. |
| plan_task_todayA | Place exactly the supplied task ID in Today, optionally at an explicit ISO timestamp. |
| start_taskA | Start tracking exactly the supplied task ID as the current task. |
| stop_timerA | Stop the Super Productivity timer without selecting or changing another task. |
| complete_taskA | Mark exactly the supplied task ID as completed. |
| get_current_taskA | Return the task currently being tracked, or null when the timer is stopped. |
| ensure_github_issue_taskA | Find an existing native or Super Productivity MCP-marked task for owner/repo#number or a GitHub issue URL. Create at most one marked task if missing; it is not planned for Today unless planToday=true. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
TDQS
Scored across 10 tools
health and check_connection have identical purpose and descriptions, making them indistinguishable. All other tools have clear, distinct roles (searching, planning, tracking, completing, GitHub integration), so the ambiguity is limited to this redundant pair.
Most tools follow a verb_noun snake_case pattern (e.g., search_tasks, start_task, complete_task). The outlier is 'health', which is a bare noun instead of a verb phrase like 'check_health' or 'get_health'. This minor deviation prevents a perfect score.
With 10 tools, the set is well-scoped for a desktop productivity API. Each tool serves a distinct function (health check, task search, today list, planning, tracking, timer control, completion, current task retrieval, GitHub integration) without unnecessary bloat.
The core workflows for Super Productivity are covered: finding tasks, planning them for today, starting/stopping time tracking, completing tasks, and retrieving the current task. Missing operations like creating standalone tasks or updating task details are notable but not critical, as the GitHub issue integration provides one creation path.