This is the MCP / AI reference for systemHUB — written for AI agents and developers. If you are a person looking for how-to help, use help.systemhub.com instead.

Guide: organise & maintain the library

Folders, moves, renames, and the habits that keep a systemHUB library navigable as it grows. Bodies are abridged and illustrative — full contracts in the tool reference.

The shape of a good library

systemHUB libraries work best organised by department, in run-order, with numbered folder prefixes so the tree reads top-to-bottom:

1. Marketing
2. Sales
3. Client Delivery
4. Finance
5. HR
6. Operations

Documents inside are named as actions (“Onboard a new client”, “Reconcile the weekly payments”) — a title should say what running the system achieves.

Working with folders

Each section has its own folder tools:

// Top-level folder — OMIT parent entirely (on the CREATE tools it must be a UUID)
→ create_folder          { "title": "3. Client Delivery" }                      // Systems
→ create_policy_folder   { "title": "HR Policies" }                             // Policies
→ create_training_folder { "title": "New Starter Training" }                    // Trainings

// Nested folder — parent is the UUID of an existing folder
→ create_folder          { "parent": "c31a9d55-…", "title": "Onboarding" }

"parent": "root" works on the READ tools, not the create ones. Since 22 Sep 2026 get_folder_tree / get_policy_tree / get_training_tree accept "root", and it means the same as omitting parent (the top level). On create_folder / create_policy_folder / create_training_folder, parent is still typed format: uuid and "root" is rejected — omit it entirely for a top-level folder. (Between 28 Aug and 22 Sep "root" was rejected everywhere, which is what earlier versions of this page said.)

Rename with rename_system_folder / rename_policy_folder / rename_training_folder; relocate documents with move_system / move_policy / move_training.

Rule: read before you restructure. Always get_folder_tree first and confirm with the user before bulk moves — folder structure is something teams navigate by muscle memory, and a “tidy up” an owner didn’t ask for is a regression, not a favour.

Keeping states honest

The review cycle runs on document states (see Document lifecycle):

Master templates

Trees include master-template content (isMasterTemplate: true) supplied from the master workspace: browsable for reference, never editable — edit/move/publish/delete all fail, and get_*_details returns 404 on them by design. When a user wants “their own version” of a master template, read the template’s structure from the tree, then create a fresh document in their folders and author it for their business.

Tags

add_document_tags / remove_document_tags attach tags to any document — useful for cross-cutting views the folder tree can’t express (e.g. tag everything touching a software tool, a compliance regime, or a client type). Keep the tag set small and deliberate; fifty ad-hoc tags are worse than none.

⚠️ Tags are case-sensitive. Sales and sales are two separate tag objects with different UUIDs, so a filter or count returns only the documents matching the exact casing. In one audited library this split a single tag across 11 documents and 2, with the same tag appearing twice in the tag list. add_document_tags matches existing tags by exact title and silently creates a new one for anything that doesn’t match — so a difference in capitalisation quietly forks your taxonomy. Read the existing tag titles before writing, and reuse them verbatim. (Verified on one pair, 28 Aug 2026; several more suspected.)

Learning tracks

For trainings, create_training_learning_track / edit_training_learning_track / remove_training_learning_tracks group training documents into ordered tracks (e.g. “New starter week 1”). Pair with get_document_training_progress to report completion per track — see the auditing guide.