Skip to main content
Glama

Server Configuration

Describes the environment variables required to run the server.

NameRequiredDescriptionDefault
TASQ_DBNoThe path to the SQLite database file. Defaults to $XDG_DATA_HOME/tasq/tasks.db.
TASQ_CONFIGNoPath to the TOML configuration file. Defaults to $XDG_CONFIG_HOME/tasq/config.toml.
TASQ_DAILY_HOURSNoOverride the daily focus hours for planning. Default from config.

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

CapabilityDetails
tools
{
  "listChanged": false
}
prompts
{
  "listChanged": false
}
resources
{
  "subscribe": false,
  "listChanged": false
}
experimental
{}

Tools

Functions exposed to the LLM to take actions

NameDescription
add_taskA

Create a task. priority is 1 (highest)–5; size is XS/S/M/L/XL; dates are ISO 'YYYY-MM-DD'; project is a project name (created if new). Pass parent_id to make this a sub-task (nesting is limited to one level). When guess_dates is true (default), a missing start date defaults to the next working day and a missing due date to a few business days later; pass false to leave dates unset.

edit_taskA

Update a task. Omit a field to leave it unchanged; pass an empty string to clear an optional field (description, project, size, dates). Set parent_id to re-parent (one level max), or clear_parent=true to detach.

link_sessionA

Link the AI agent session you're working in to a task, so it can be resumed later. agent is 'claude-code' or 'github-copilot-cli'; directory is the absolute working directory of this session; session_id is this session's own id (used with --resume) if you know it; launcher is the command or shell alias used to start the agent (it selects the profile, e.g. 'claude-work') — omit to use the agent's default command. Re-linking replaces any previous link. Call this when you start or resume work on a task.

unlink_sessionA

Remove the AI session link from a task.

flag_attentionA

Flag a task as awaiting the user's attention — e.g. you need a decision or input to proceed. note should say what you need (a short question). This makes the task stand out and rings a bell in the user's interactive board. Call clear_attention once the user has responded.

clear_attentionA

Clear a task's 'needs attention' flag once the user has responded.

ingestA

Sync external items into tasks, deduplicated by (source, external_id).

    Each item needs 'external_id' (the stable dedup key within `source`) and
    'title'; optional: description, url, project, labels, priority (1–5), size,
    scheduled_date, due_date (ISO). Re-running upserts instead of duplicating:
    new items are created, existing non-terminal ones have their title/description
    refreshed (your triage is kept), terminal ones are left alone. With
    `close_missing`, previously-ingested tasks absent from this batch are completed.
get_taskC

Full task detail including status history and extracted references.

list_tasksB

List tasks with structured filters. By default terminal tasks (completed/cancelled) are hidden unless include_terminal is true. Use parent_id for one task's sub-tasks, or top_level_only to hide sub-tasks.

search_tasksA

Fuzzy-search tasks over title and description; ranked, best first.

search_referencesB

Search URLs extracted from task descriptions (fuzzy on url + anchor).

transition_taskA

Change a task's status, recording the transition (comment optional). Statuses: waiting, in_progress, blocked, completed, cancelled.

agendaC

Overdue, today, upcoming (next N days), and in-progress/blocked tasks.

planA

Propose a non-persistent day-by-day schedule of open tasks, greedily packed into a daily focus budget (default from config) and ordered by started-then-priority-then-due. Counts working days — weekends are skipped unless include_weekends. Narrow the candidates with projects/labels (include) or exclude_labels (drop private work); each falls back to config. The suggested day is not saved to the task.

add_projectC

Create a project. Project labels describe the project (e.g. the company).

list_projectsD

List projects.

archive_projectA

Archive a project (kept, not deleted).

list_labelsA

List labels WITH descriptions — read these to know what each label means and when to apply it before labelling or prioritising.

describe_labelA

Set or update a label's description (creates the label if new).

Prompts

Interactive templates invoked by user choice

NameDescription

No prompts

Resources

Contextual data attached and managed by the client

NameDescription
labels_resourceThe full label taxonomy with descriptions, as Markdown context.
agenda_today_resource
agenda_upcoming_resource

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/ptucholski/tasq'

If you have feedback or need assistance with the MCP directory API, please join our Discord server