Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| PORT | No | HTTP server port (when TRANSPORT=http) | 4680 |
| DEBUG | No | If true, enable the tasks_debug tool | false |
| AUTO_WIP | No | One WIP moves rest to To Do, first To Do to WIP when no WIP's | true |
| STATUSES | No | Comma-separated additional statuses | Backlog |
| TRANSPORT | No | Transport mode: stdio or http | stdio |
| STATUS_WIP | No | Work-in-progress status name | In Progress |
| STATUS_DONE | No | Completed status name | Done |
| STATUS_TODO | No | ToDo status name | To Do |
| INSTRUCTIONS | No | Included in all tool responses, for the AI to follow | |
| KEEP_DELETED | No | Retain deleted tasks (AI can't lose you tasks!) | true |
| PREFIX_TOOLS | No | Prefix tool names with tasks_ | true |
| SOURCES_PATH | No | File to store source registry (internal) | ./sources.json |
| STATUS_NOTES | No | Optional notes/non-actionable status name | Notes |
Schema
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
No resources | |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| tasks_setup | Initializes an source file from a path
|
| tasks_search | Search tasks from specific statuses with optional text & ID filtering |
| tasks_add | Add new tasks with a specific status. It's faster and cheaper if you use this in batch. User can add atomically while AI works using the CLI add tool |
| tasks_update | Update tasks in bulk by ID to a different status. Returns complete summary no need to call tasks_summary afterwards. Prevents AI accidentally rename or deleting tasks during mass updates, not even possible |
| tasks_summary | Get per-status task counts and the WIP task(s). Redundant right after tasks_add/tasks_update |