Task Manager MCP Server
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| DEEPSEEK_API_KEY | No | Your DeepSeek API key for AI-powered features. Optional; the server includes a default key for testing, but set your own for production. |
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 | {} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| create_taskC | Create a new task in the task board. |
| get_taskC | Get a task by its ID. |
| list_tasksB | List tasks with optional filtering by category, status, or tags. |
| update_taskC | Update an existing task. |
| delete_taskC | Delete a task by ID. |
| get_daily_logB | Get daily log for a specific date (YYYY-MM-DD). Defaults to today. |
| plan_dayC | Plan tasks for a specific date. Adds task IDs to planned_task_ids. |
| complete_tasksB | Mark tasks as completed for a specific date. Updates daily log and task status. |
| list_daily_logsB | List daily logs within a date range. |
| get_projectionsB | Get current projections including velocity and forecast. |
| update_velocityC | Update velocity (tasks/day) based on recent completion data. |
| forecast_completionC | Generate forecast for when tasks will be completed based on current velocity. |
| scan_recent_sessionsC | Scan recent agent-modes sessions for context notes that may indicate task completion. |
| recommend_daily_tasksB | AI-recommended task selection for today based on priority, dependencies, and recent progress. |
| get_daily_summaryB | Generate summary of a daily log including completion rate and category breakdown. |
| analyze_session_for_tasksB | Use AI to analyze agent-modes session context notes for task completion and progress. |
| parse_natural_language_taskC | Convert natural language task description into structured task data using AI. |
| generate_weekly_summaryC | Generate AI-written weekly productivity summary from daily logs. |
| summarize_task_descriptionC | Use AI to create a concise, clear summary of a task description. |
| recommend_daily_tasks_aiB | AI-powered task recommendation using DeepSeek (more sophisticated than rule-based). |
| display_task_boardB | Generate a visual task board in markdown format with columns for each status. |
| seed_tasks_from_projectsB | Scan the projects directory and create initial tasks for each project folder. |
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 22 tools
Several tools have overlapping purposes, most notably recommend_daily_tasks vs recommend_daily_tasks_ai and scan_recent_sessions vs analyze_session_for_tasks, where the descriptions do not clearly indicate when to choose one over the other. get_projections and forecast_completion also overlap, creating potential misselection.
All tool names use snake_case and generally follow a verb_noun pattern (e.g., create_task, get_task, update_task, delete_task, list_tasks). Minor variations like the _ai suffix or multi-word nouns are consistent with the overall convention.
With 22 tools, the server is on the heavy side for a task manager, and several overlapping AI/session analysis tools could likely be consolidated. The count is borderline but not extreme given the breadth of features.
Core task CRUD is fully covered, along with daily logs, planning, and forecasting. However, there are no explicit tools for managing task dependencies, categories/tags, or project entities, which are minor gaps agents can work around.