Task Orchard
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Task Orchard what should I work on next?"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
Task Orchard
A task and time management service for one person, used through an AI assistant over MCP.
You cultivate trees of tasks: big vague efforts, one-line reminders, recurring chores, things you want to do more of. In return the assistant helps you decide what to work on when you need it, using facts the server computes and what it has learned about how your work actually goes.
Status: scaffold and schema only. The server starts and serves one tool (get_guide). The task tools are specified in docs/SPEC.md and not yet built.
Documents
File | What it is |
The feature specification: every operation, phase by phase, with acceptance tests. | |
The design and the reasoning behind it. | |
The original idea. | |
Working notes for whoever implements it. |
Related MCP server: MCP Task Management Server
Quick start
Requires Python 3.12 or later and uv.
uv sync
uv run pytest
uv run task-orchard infoConfiguration
Variable | Meaning | Default |
| Path to the SQLite database file. |
|
| Your timezone as an IANA name, such as | The system timezone, else UTC. |
The database is created and migrated automatically on first start.
Connecting an MCP client
Task Orchard runs as a stdio MCP server. In your client, add a server whose command is:
uv run --directory /path/to/this/repo task-orchardand set TASK_ORCHARD_TZ in that server's environment if your system timezone is not the one you want.
Trying it with demo data
TASK_ORCHARD_DB=/tmp/orchard-demo.db uv run task-orchard seed-demoThis fills a new database with a small realistic set of tasks (projects, blockers, an inbox, scheduled and flexible recurring tasks, history). Point your MCP client at the same TASK_ORCHARD_DB to explore it. The contents are described at the top of src/task_orchard/devtools/seed.py.
Available Tools
1 toolget_guideGet GuideA
Read one of Task Orchard's guides: step-by-step instructions for a job.
Call with no name to list the guides. Call with a name to get its text, then follow it.
Inputs: name. Returns: object
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 1 tool
With only one tool, there is no possibility of misselection or overlapping purpose. The tool's role is unambiguous.
The single name get_guide follows a clear verb_noun snake_case convention. Only one data point exists, so consistency across the set cannot be fully demonstrated.
One tool is thin for a server whose domain is browsing and consuming multiple guides. It is workable but feels under-scoped for even a read-only surface.
Listing and fetching guide text are covered, but there is no search, categorization, or metadata operation to help an agent find the right guide among many. For a read-only guide service this is notable but not fatal.
Maintenance
Related MCP Connectors
ADHD system of record for agents: tasks, goals, loops, calendar, focus stats.
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
Task management for people and AI agents, with scoped OAuth access to issues, projects, and docs.
Project management for AI agents: tasks, docs, decisions and time in one shared team context.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceEnables AI assistants to create, manage, and break down tasks into subtasks with priorities, and track progress through a hierarchical task list.8 npm12GPL 3.0
- AlicenseAqualityDmaintenanceEnables comprehensive task management with groups, custom statuses, and task relationships, designed for AI assistants to manage tasks during conversations.17ISC
- AlicenseNot gradedqualityBmaintenanceProvides 13 tools for AI agents to manage tasks, calendar, and goals in TaskPilot, a local-first desktop task manager with a permissioned agent runner and review workflows.MIT
- AlicenseNot gradedqualityBmaintenanceEnables an AI agent to manage personal tasks, calendar events, and projects through 12 tools covering CRUD operations, cross-entity search, daily analysis, and multi-step action planning. Supports natural-language requests that are orchestrated into real actions with real-time streaming updates.84 npmMIT