tidy
Server Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| TIDY_HOME | No | Directory for plans and undo logs (default: ~/.tidy). | |
| TIDY_LIMIT | No | Maximum number of files per run (default: 500). Can also be set in ~/.tidy/config.toml as limit. | |
| TIDY_IGNORE | No | File name patterns to leave alone, e.g. "*.part,keep-*". Can also be set in ~/.tidy/config.toml as ignore. | |
| TIDY_WORKERS | No | Number of files to describe at once (default: 4). Can also be set in ~/.tidy/config.toml as workers. | |
| TIDY_TEXT_MODEL | No | Ollama model for text files (default: qwen2.5:7b). Can also be set in ~/.tidy/config.toml as text_model. | |
| TIDY_VISION_MODEL | No | Ollama model for image files (default: qwen2.5vl:7b). Can also be set in ~/.tidy/config.toml as vision_model. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
tidy organizes messy folders with a local AI. Always call plan_tidy first, show the user every change in the plan, and call apply_plan only after the user agrees. Files are never deleted; duplicates and old installers go to _tidy_trash. Every applied plan can be reversed with undo.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": false
} |
| prompts | {
"listChanged": false
} |
| resources | {
"subscribe": false,
"listChanged": false
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| scan_folderB | List the files tidy would look at in a folder (top level only, no hidden files). |
| describe_fileB | Ask the local model for a better name and folder for one file. |
| plan_tidyB | Build a dry-run plan for a folder. Nothing is moved. Show the plan to the user. |
| apply_planA | Apply a plan the user has approved. Files are moved, never deleted. |
| undoA | Put every file from an applied plan back where it was. |
| find_duplicatesC | Groups of identical files. The first in each group is the original and is kept. |
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 6 tools
Each tool maps to a distinct step in the tidy workflow (scan, plan, apply, undo) plus two focused helpers (find_duplicates, describe_file). The only mild overlap is scan_folder vs plan_tidy, since both inspect a folder, but descriptions make clear one lists and the other builds a dry-run plan.
Nearly all tools follow a verb_noun pattern (scan_folder, plan_tidy, apply_plan, find_duplicates, describe_file). The bare 'undo' deviates slightly, but it's a universally understood single-action name and remains readable.
Six tools is well within the sweet spot and every tool earns its place in the workflow. Nothing feels redundant or missing from the count perspective.
The surface covers the full lifecycle: scan, dry-run plan, apply, undo, plus duplicate detection and per-file LLM suggestions. Minor gaps exist, such as no way to selectively edit or exclude items in a plan, no history of past plans, and no explicit action to actually relocate detected duplicates.