kanopy
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| KANOPY_KEY | No | Optional; stored as the admin's API token on start, for older agent configs. | |
| KANOPY_URL | No | Public address when behind a reverse proxy. | |
| KANOPY_HOST | No | Address to listen on. | 127.0.0.1 |
| KANOPY_PORT | No | Port to listen on. | 8000 |
| KANOPY_DATABASE | No | A postgresql://user:pass@host/db URL to use PostgreSQL instead of SQLite. | data/kanban.db |
| KANOPY_UPDATE_CHECK | No | 0 stops the server asking GitHub for the latest release (shown to admins in Settings). | 1 |
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 |
|---|---|
| list_projectsC | Project tree with open-task counts. |
| save_projectA | Update a project: move to path, description, folder, archived. New projects are made by save_task with a new project path, so none is ever empty. |
| list_tasksB | Tasks as compact lines under [project] headers. Filters AND together. |
| get_taskB | Full tasks: description, relations, the last 5 comments. file= returns one attachment's text instead. |
| save_taskB | Create (project + title) or update by id; only given fields change. |
| commentC | Add a markdown progress note to a task. |
| linkC | Relate two tasks, or remove the relation. |
| labelsB | List global labels and your own. create: add a global type: value (admin, only when asked). delete: remove one of your labels everywhere (global ones: admin). |
| inboxA | Your unread notifications; read=true marks them all read. |
| deleteA | Delete a task (kept in the trash 30 days) or an empty project. Confirm first. restore= brings a deleted task back. |
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
Most tools have clearly distinct purposes: list_projects vs list_tasks, get_task vs list_tasks, and save_task vs save_project are all separable by resource and action. The main fuzziness is that project creation happens inside save_task (save_project only updates), and delete/labels are multi-resource or multi-action tools whose scope must be read carefully.
Half the set follows verb_noun (list_projects, save_project, get_task, list_tasks, save_task), but the rest are bare nouns or verbs (comment, link, labels, inbox, delete), and several tools hide multiple actions behind a single name. It remains readable, but there is no single predictable pattern an agent can extrapolate from.
Ten tools is well within the ideal range and each one maps to a real part of a project/task workflow (projects, tasks, comments, relations, labels, notifications, trash). No tool feels redundant or padded.
CRUD is largely covered for tasks (save_task, get_task, list_tasks, delete/restore) and projects (list/save/delete, creation via save_task), plus links, labels, comments, and inbox. Gaps remain: comments can be added but not edited or deleted, and get_task can read attachment text but there is no tool to upload or attach a file.