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.

This page is generated from the live systemHUB MCP schemas. A hand-written reference drifts, and a client’s AI flails when the docs say X and the tool does Y. This reference is regenerated from the schema snapshot on every deploy so it cannot lie. Guides and examples are hand-written; this reference is not.

Because it mirrors the schema faithfully, it also reproduces the schema’s known inaccuracies until they’re fixed upstream. Where this page conflicts with the concepts pages, the concepts pages win — currently one known case: the schema describes description as “plain-text”, but the field holds rich text (it’s the Overview, same editor rules as the body — see Authoring content). A schema fix is logged.

⚠️ This page was generated from a stored schema snapshot, not a live fetch. The snapshot was last refreshed 0 days ago, so newer tools or changed parameters may be missing. The live pull now requires a human to approve an OAuth consent screen (a deliberate security change), so it can no longer run unattended. Call tools/list on your own connection if you need the authoritative set, and treat anything here as accurate as of the snapshot rather than as of today.

Documents are addressed by UUID. States are integers — see Document lifecycle (0 GREY draft · 1 ORANGE needs-review · 2 RED overdue · 3 GREEN approved · 4 PURPLE archived). Node/item type: 1 = FOLDER, 2 = DOCUMENT.

Discovery & navigation

get_folder_tree

Returns the hierarchical folder and document tree for the Systems section of SystemHub. Each node includes its ID, title, type (1=FOLDER, 2=DOCUMENT), document state, owner full name, ownerId for filtering, optional secondary owner full name, publication status, isMasterTemplate, isRootMasterTemplate, and nested children when depth > 1. Optionally scope the result to a specific subtree by providing a parent folder UUID, or pass parent “root” (same as omitting parent) for the section root. Filter by type to get only folders or only documents. Filter by role to see items assigned to a specific role. Use this tool first to understand the organizational structure before navigating to specific documents. Default depth is 1 (this level only — nested children are omitted) so large libraries do not overflow the client. Paginate top-level nodes with page/limit (default 50). To expand a folder, call again with parent set to that folder UUID and depth 1. parent “root” is accepted and means the section root (same as omitting parent). For a flat paginated folder list, list_documents_by_owner with type: 1 also works. Before authoring, call get_authoring_contract or read https://systemhub.com/llms-full.txt (raw HTML not entity-escaped; H1–H3 only; four marker-* highlights; Trigger, then h3 steps, then Definition of done). Use ownerId for programmatic owner-based filtering. Results include both operational content (company-owned) and master templates (read-only reference content from the master workspace). Each node/item has isMasterTemplate; tree nodes also have isRootMasterTemplate. When the user asks about their own content, filter to isMasterTemplate=false. Do not edit, delete, move, or publish master templates. get_*_details on master template documents returns 404 — content lives in the master workspace only. Templates appear in trees for browsing.

ℹ️ Three known issues (ours, logged, unfixed). The parameters above are current — call bare first, then open one folder at a time with its id and depth: 1. What the schema does not tell you: the role filter is ignored and the full result comes back whatever role you pass · a template folder cannot be opened by its own id, because that id is literally "root" (AI & Templates in Systems and Policies, Courses in Trainings) and collides with parent: "root" — raise depth from the top level instead (e.g. depth: 3) · owner comes back as an id, not the full name the description promises, and there is no ownerId field.

Returns

get_policy_tree

Returns the hierarchical folder and document tree for the Policies section of SystemHub. Each node includes its ID, title, type (1=FOLDER, 2=DOCUMENT), document state, owner full name, ownerId for filtering, optional secondary owner full name, publication status, isMasterTemplate, isRootMasterTemplate, and nested children when depth > 1. Optionally scope the result to a specific subtree by providing a parent folder UUID, or pass parent “root” (same as omitting parent) for the section root. Filter by type to get only folders or only documents. Filter by role to see items assigned to a specific role. Default depth is 1 (this level only — nested children are omitted) so large libraries do not overflow the client. Paginate top-level nodes with page/limit (default 50). To expand a folder, call again with parent set to that folder UUID and depth 1. parent “root” is accepted and means the section root (same as omitting parent). For a flat paginated folder list, list_documents_by_owner with type: 1 also works. Use ownerId for programmatic owner-based filtering. Results include both operational content (company-owned) and master templates (read-only reference content from the master workspace). Each node/item has isMasterTemplate; tree nodes also have isRootMasterTemplate. When the user asks about their own content, filter to isMasterTemplate=false. Do not edit, delete, move, or publish master templates. get_*_details on master template documents returns 404 — content lives in the master workspace only. Templates appear in trees for browsing.

ℹ️ Three known issues (ours, logged, unfixed). The parameters above are current — call bare first, then open one folder at a time with its id and depth: 1. What the schema does not tell you: the role filter is ignored and the full result comes back whatever role you pass · a template folder cannot be opened by its own id, because that id is literally "root" (AI & Templates in Systems and Policies, Courses in Trainings) and collides with parent: "root" — raise depth from the top level instead (e.g. depth: 3) · owner comes back as an id, not the full name the description promises, and there is no ownerId field.

Returns

get_training_tree

Returns the hierarchical folder and training document tree for the Training section of SystemHub. Each node includes its ID, title, type (1=FOLDER, 2=DOCUMENT), document state, owner full name, ownerId for filtering, optional secondary owner full name, publication status, isMasterTemplate, isRootMasterTemplate, and nested children when depth > 1. Optionally scope the result to a specific subtree by providing a parent folder UUID, or pass parent “root” (same as omitting parent) for the section root. Filter by type to get only folders or only trainings. Filter by role to see items assigned to a specific role. Use this tool first to understand the organizational structure before navigating to specific trainings. Default depth is 1 (this level only — nested children are omitted) so large libraries do not overflow the client. Paginate top-level nodes with page/limit (default 50). To expand a folder, call again with parent set to that folder UUID and depth 1. parent “root” is accepted and means the section root (same as omitting parent). For a flat paginated folder list, list_documents_by_owner with type: 1 also works. Use ownerId for programmatic owner-based filtering. Results include both operational content (company-owned) and master templates (read-only reference content from the master workspace). Each node/item has isMasterTemplate; tree nodes also have isRootMasterTemplate. When the user asks about their own content, filter to isMasterTemplate=false. Do not edit, delete, move, or publish master templates. get_*_details on master template documents returns 404 — content lives in the master workspace only. Templates appear in trees for browsing.

ℹ️ Three known issues (ours, logged, unfixed). The parameters above are current — call bare first, then open one folder at a time with its id and depth: 1. What the schema does not tell you: the role filter is ignored and the full result comes back whatever role you pass · a template folder cannot be opened by its own id, because that id is literally "root" (AI & Templates in Systems and Policies, Courses in Trainings) and collides with parent: "root" — raise depth from the top level instead (e.g. depth: 3) · owner comes back as an id, not the full name the description promises, and there is no ownerId field.

Returns

search_by_name

Searches for system documents and folders by title using case-insensitive partial matching. To search document bodies/URLs, use search_content. By default each match returns only id, title, type (1=FOLDER, 2=DOCUMENT), state, and owner. HTML bodies, tags, templates, videos, attachments, comments, and share links are omitted, and those lookups are skipped. Pass fields (for example [“title”,“state”,“isMasterTemplate”]) to add columns. Pass full: true, or fields: [""], for the complete payload. Breaking change: omitting fields used to return the full result; pass full: true to keep that behaviour. Use page and limit to paginate. Useful when you don’t know a document’s UUID or folder. Use ownerId for programmatic owner-based filtering. REQUIRED: When presenting document details/content, place Share link immediately after Notes. When shareLink is present, always show the full URL (including search results) — this is the same link users copy from the SystemHub UI and opens in a browser. Never hide an existing share link. When shareLink is null, show “Not available” and suggest get_document_share_link if they need one. When presenting document.content HTML (including from search results): render the content faithfully — do not paraphrase or invent surrounding sentences. Any hyperlink in the document must be shown only as its anchor text as a clickable link (e.g. markdown anchor text). Do not add prefixes such as “Link:”, “Additional link:”, or similar. Do not describe the link in prose. Do not append the raw URL in parentheses after the label. If the anchor has no label, show the URL itself as plain linked text. isMasterTemplate is omitted from the default listing. Include it in fields, or pass full: true, before calling get__details — master template documents return 404 there. When the user asks about their own content, filter to isMasterTemplate=false. Do not edit, delete, move, or publish master templates.

Returns

search_policy

Searches for policy documents and folders by title using case-insensitive partial matching. To search document bodies/URLs, use search_content. By default each match returns only id, title, type (1=FOLDER, 2=DOCUMENT), state, and owner. HTML bodies, tags, templates, videos, attachments, comments, and share links are omitted, and those lookups are skipped. Pass fields (for example [“title”,“state”,“isMasterTemplate”]) to add columns. Pass full: true, or fields: [""], for the complete payload. Breaking change: omitting fields used to return the full result; pass full: true to keep that behaviour. Use page and limit to paginate. Use ownerId for programmatic owner-based filtering. REQUIRED: When presenting document details/content, place Share link immediately after Notes. When shareLink is present, always show the full URL (including search results) — this is the same link users copy from the SystemHub UI and opens in a browser. Never hide an existing share link. When shareLink is null, show “Not available” and suggest get_document_share_link if they need one. When presenting document.content HTML (including from search results): render the content faithfully — do not paraphrase or invent surrounding sentences. Any hyperlink in the document must be shown only as its anchor text as a clickable link (e.g. markdown anchor text). Do not add prefixes such as “Link:”, “Additional link:”, or similar. Do not describe the link in prose. Do not append the raw URL in parentheses after the label. If the anchor has no label, show the URL itself as plain linked text. isMasterTemplate is omitted from the default listing. Include it in fields, or pass full: true, before calling get__details — master template documents return 404 there. When the user asks about their own content, filter to isMasterTemplate=false. Do not edit, delete, move, or publish master templates.

Returns

search_training

Searches for training documents and folders by title using case-insensitive partial matching. To search document bodies/URLs, use search_content. By default each match returns only id, title, type (1=FOLDER, 2=DOCUMENT), state, and owner. HTML bodies, tags, templates, videos, attachments, comments, and share links are omitted, and those lookups are skipped. Pass fields (for example [“title”,“state”,“isMasterTemplate”]) to add columns. Pass full: true, or fields: [”*”], for the complete payload. Breaking change: omitting fields used to return the full result; pass full: true to keep that behaviour. Learning tracks are omitted unless requested in fields or full: true. Use page and limit to paginate. Use ownerId for programmatic owner-based filtering. REQUIRED: When presenting document details/content, place Share link immediately after Notes. When shareLink is present, always show the full URL (including search results) — this is the same link users copy from the SystemHub UI and opens in a browser. Never hide an existing share link. When shareLink is null, show “Not available” and suggest get_document_share_link if they need one.

Returns

search_content

Searches document bodies for a literal substring — overview/details/notes, including URLs and phrases. Use this for body/URL/phrase audits. Use search_by_name / search_policy / search_training for titles. Results are snippets only; call get_system_details / get_policy_details / get_training_details only for documents you will edit. Pair with edit_system_content, edit_policy_content, or edit_training_content for surgical find/replace.

Returns

list_documents_by_owner

Returns a flat, paginated list of SystemHub documents (systems + policies + trainings) — in one call, without per-document detail requests. Each item includes id, title, type (1=FOLDER, 2=DOCUMENT), state, section (discriminator), folder path (materializedPath), and owner metadata. Omit owner, secondaryOwner, and roleId to list every item the caller can see (use type: 1 for a company-wide folder list). filterApplied is false in that case. Use owner or secondaryOwner as a user UUID or full name to narrow results. Use ownership=either (default) to find documents where someone is primary OR distinct secondary owner. Use roleId to filter by assigned role. Omit section to search all three areas at once. Set fetchAll=true to retrieve every matching document across pages (up to 5000). Use ownerId for programmatic owner-based filtering.

Returns

Reading documents

get_system_details

Retrieves details of a system document by UUID. By default returns the full payload (title, state, HTML content, description, notes, tags, templates, Videos & Media, attachments, comments, owners, review date, last modified, published version, isMasterTemplate, shareLink). Pass fields (e.g. [“title”,“description”,“note”]) to return only those properties and skip expensive side fetches — use this for audits/overviews so you do not download full HTML bodies. Check isMasterTemplate from tree/search before calling — master template documents return 404 here. CRITICAL: If shareLink is a non-null URL, you MUST display it in a Share link section whenever you present document details or content — never omit an existing share link.

Returns

get_policy_details

Retrieves details of a policy document by UUID. By default returns the full payload (title, state, HTML content, description, notes, tags, templates, Videos & Media, attachments, comments, owners, review date, last modified, published version, isMasterTemplate, shareLink). Pass fields (e.g. [“title”,“description”,“note”]) to return only those properties and skip expensive side fetches — use this for audits/overviews so you do not download full HTML bodies. Check isMasterTemplate from tree/search before calling — master template documents return 404 here. CRITICAL: If shareLink is a non-null URL, you MUST display it in a Share link section whenever you present document details or content — never omit an existing share link.

Returns

get_training_details

Retrieves details of a training document by UUID. By default returns the full payload (title, state, HTML content, description, notes, tags, templates, Videos & Media, attachments, comments, learning tracks, owners, review date, last modified, published version, isMasterTemplate, shareLink). Pass fields (e.g. [“title”,“description”,“note”]) to return only those properties and skip expensive side fetches — use this for audits/overviews so you do not download full HTML bodies. Check isMasterTemplate from tree/search before calling — master template documents return 404 here. CRITICAL: If shareLink is a non-null URL, you MUST display it in a Share link section whenever you present document details or content — never omit an existing share link.

Returns

Access, agreement & progress

get_document_members_and_roles

Retrieves assigned members and roles for a system, policy, or training document. Returns roles assigned to the document plus each member’s name, email, role title(s), and access type (direct assignment, role-based, or both). Use after finding the document UUID via search_by_name, search_policy, or search_training. Respects the authenticated user’s visibility scope. Set fetchAll=true (default) for a complete access audit.

Returns

get_document_agreement_status

Retrieves sign-off / agreement status for a system, policy, or training document. Returns who is currently signed off, who agreed against an earlier published body, and who is still pending among users assigned to the document. A sign-off is stale when a later published version changed the document body. Use after finding the document UUID via search_by_name, search_policy, or search_training. Respects the authenticated user’s visibility scope on the item API. Set fetchAll=true (default) for a complete audit list.

Returns

get_document_training_progress

Retrieves learning completion progress for a training document. Returns each assigned user’s percentage complete (based on learning track sign-offs), status (complete, in progress, or not started), and last update time. Use after finding the training UUID via search_training or get_training_details. Respects the authenticated user’s visibility scope. Set fetchAll=true (default) for a complete audit list.

Returns

get_document_activity_log

Retrieves the activity / audit trail for a system, policy, or training document. Returns who created it and when, who last modified it (with change summary when available), and a chronological feed of significant create/modify events. Use after finding the document UUID via search_by_name, search_policy, search_training, or get_*_details. Answers questions like “Who created this system?” and “Who last edited this policy?”. Respects the authenticated user’s view permissions on the item API. Set fetchAll=true (default) for a complete history. Present activity as an audit summary: lead with creation (who/when) and last modification (who/when/what), then list significant events chronologically. Prefer full names and emails. When agentCall is true, say the change was made via MCP. Skip routine view events unless the user explicitly asks for views.

⚠️ Two limits the schema does not mention. Events recorded before the 19 Oct 2026 release are unlabelled, so the absence of agentCall: true on an older event proves nothing · writes made with a company API key are not flagged yet and still look like app edits, so read agentCall: false as “not through MCP”, never as “a human did this”.

Returns

Sharing, members & roles

get_document_share_link

Retrieves the public share URL for a system, policy, or training document. Reuses the existing share code when present (typical — share codes are assigned when documents are created); creates one only when missing. Requires SHARE permission for the document type. Use after finding the document UUID via search_by_name, search_policy, search_training, or get_*_details. Returns shareLink as the same human-facing URL shown in the SystemHub UI. REQUIRED: When presenting document details/content, place Share link immediately after Notes. When shareLink is present, always show the full URL (including search results) — this is the same link users copy from the SystemHub UI and opens in a browser. Never hide an existing share link. When shareLink is null, show “Not available” and suggest get_document_share_link if they need one.

Returns

manage_document_members

Adds, removes, or updates assigned members and roles on a system, policy, or training document. Use action=add|remove with userIds for direct member access, and/or roleIds for company roles assigned to the document. When the user gives a person or role name (not UUID), call list_company_members (search) or list_roles (title) first — never ask the user to look up UUIDs. Use action=update with roleIds to replace the document’s assigned roles. Requires document UPDATE (or role-assignment) permission. Verify results afterward with get_document_members_and_roles.

Returns

list_company_members

Lists company members and resolves people by name or email to UUIDs. Use when the user names someone (e.g. “Ariel Tester”) before manage_document_members, which requires userIds. Filter with search for a full name or email; check exactNameMatch for an exact name hit. Returns userId, fullName, email, userType, and position.

Returns

list_roles

Lists company roles and resolves role names to UUIDs. Use when the user names a role (e.g. “Tech Team”) before manage_document_members, which requires roleIds. Filter with title for case-insensitive partial match; check exactTitleMatch for an exact name hit. Returns roleId, title, description, and membersAmount.

Returns

Creating content

create_system

Creates a new system document inside an existing folder. Requires the parent folder UUID (use get_folder_tree to find one) and a title. Optionally provide content (HTML), description, note, and state in the same call. The document is always published right after creation so it is visible outside edit mode — do not ask the user to confirm publishing.

Returns

create_policy

Creates a new policy document inside an existing folder. Requires the parent folder UUID (use get_policy_tree to find one) and a title. Optionally provide content (HTML), description, note, and state in the same call. The document is always published right after creation so it is visible outside edit mode — do not ask the user to confirm publishing.

Returns

create_training

Creates a new training document inside an existing folder. Requires the parent folder UUID (use get_training_tree to find one) and a title. Optionally provide content (HTML), description, note, and state in the same call. The document is always published right after creation so it is visible outside edit mode — do not ask the user to confirm publishing.

Returns

create_folder

Creates a new folder in the Systems section of SystemHub. Folders organize system documents hierarchically. Provide a title for the folder and optionally a parent folder UUID to nest it under an existing folder. Omitting the parent creates a root-level folder. Returns the created folder’s ID, title, and type.

Returns

create_policy_folder

Creates a new folder in the Policies section of SystemHub. Folders organize policy documents hierarchically. Provide a title for the folder and optionally a parent folder UUID to nest it under an existing folder. Omitting the parent creates a root-level folder. Returns the created folder’s ID, title, and type.

Returns

create_training_folder

Creates a new folder in the Training section of SystemHub. Training folders organize training documents hierarchically. Provide a title for the folder and optionally a parent folder UUID to nest it under an existing folder. Omitting the parent creates a root-level folder. Returns the created folder’s ID, title, and type.

Returns

Editing & publishing

get_authoring_contract

Returns the systemHUB document formatting contract as structured data: allowed HTML (H1–H3 only, four marker-* highlights), field mapping (title/overview/details/notes), house structure (Trigger, h3 steps, Definition of done), and known issues. Call this before create_system / create_policy / create_training or any content edit. Does not require a web fetch. Full corpus: https://systemhub.com/llms-full.txt.

No parameters.

Returns

edit_system

Updates an existing system document’s fields. Provide the document UUID and any combination of fields to update: title, content (HTML string), description, note, state (0=GREY, 1=ORANGE, 2=RED, 3=GREEN, 4=PURPLE), reviewDate, owner (primary owner UUID), or secondaryOwner (secondary owner UUID, or null to remove). Only provided fields are changed; omitted fields remain untouched. For small text/link fixes inside HTML content, prefer edit_system_content (find/replace) instead of resupplying the full content string. Edits are always published automatically so assigned users can see them — do not ask the user to confirm publishing. Use reviewDate on edit_system, edit_policy, or edit_training to add, update, or remove a review date (ISO 8601; must be today or in the future; pass null to remove). Omit reviewDate to leave it unchanged. Review date changes are saved and published automatically in the background — do not mention publishing, versions, draft/publish status, or the published field in the tool response to the user. After editing reviewDate, confirm the saved date only from the reviewDate field in the tool output — never assume success from the user request alone. If reviewDate in the output does not match what was requested, report that the update failed. To mark overdue, set state: 2 (RED) separately.

Returns

edit_policy

Updates an existing policy document’s fields. Provide the document UUID and any combination of fields to update: title, content (HTML string), description, note, state (0=GREY, 1=ORANGE, 2=RED, 3=GREEN, 4=PURPLE), reviewDate, owner (primary owner UUID), or secondaryOwner (secondary owner UUID, or null to remove). Only provided fields are changed; omitted fields remain untouched. For small text/link fixes inside HTML content, prefer edit_policy_content (find/replace) instead of resupplying the full content string. Edits are always published automatically so assigned users can see them — do not ask the user to confirm publishing. Use reviewDate on edit_system, edit_policy, or edit_training to add, update, or remove a review date (ISO 8601; must be today or in the future; pass null to remove). Omit reviewDate to leave it unchanged. Review date changes are saved and published automatically in the background — do not mention publishing, versions, draft/publish status, or the published field in the tool response to the user. After editing reviewDate, confirm the saved date only from the reviewDate field in the tool output — never assume success from the user request alone. If reviewDate in the output does not match what was requested, report that the update failed. To mark overdue, set state: 2 (RED) separately.

Returns

edit_training

Updates an existing training document’s fields. Provide the training UUID and any combination of fields to update: title, content (HTML string), description, note, state (0=GREY, 1=ORANGE, 2=RED, 3=GREEN, 4=PURPLE), reviewDate, owner (primary owner UUID), or secondaryOwner (secondary owner UUID, or null to remove). Only provided fields are changed; omitted fields remain untouched. For small text/link fixes inside HTML content, prefer edit_training_content (find/replace) instead of resupplying the full content string. Edits are always published automatically so assigned users can see them — do not ask the user to confirm publishing. Use reviewDate on edit_system, edit_policy, or edit_training to add, update, or remove a review date (ISO 8601; must be today or in the future; pass null to remove). Omit reviewDate to leave it unchanged. Review date changes are saved and published automatically in the background — do not mention publishing, versions, draft/publish status, or the published field in the tool response to the user. After editing reviewDate, confirm the saved date only from the reviewDate field in the tool output — never assume success from the user request alone. If reviewDate in the output does not match what was requested, report that the update failed. To mark overdue, set state: 2 (RED) separately.

Returns

edit_system_content

Performs surgical find-and-replace on a system document’s HTML content without requiring the agent to resupply the full body. Provide id and replacements: [{ find, replace }, …]. Replacements are literal (not regex) and applied sequentially. Errors if any find string is missing (never silently no-ops) or if expectMatches is set and the total match count differs. Prefer this over edit_system for small text/link fixes to save tokens and avoid HTML transcription errors. Edits are always published automatically.

Returns

edit_policy_content

Performs surgical find-and-replace on a policy document’s HTML content without requiring the agent to resupply the full body. Provide id and replacements: [{ find, replace }, …]. Replacements are literal (not regex) and applied sequentially. Errors if any find string is missing (never silently no-ops) or if expectMatches is set and the total match count differs. Prefer this over edit_policy for small text/link fixes to save tokens and avoid HTML transcription errors. Edits are always published automatically.

Returns

edit_training_content

Performs surgical find-and-replace on a training document’s HTML content without requiring the agent to resupply the full body. Provide id and replacements: [{ find, replace }, …]. Replacements are literal (not regex) and applied sequentially. Errors if any find string is missing (never silently no-ops) or if expectMatches is set and the total match count differs. Prefer this over edit_training for small text/link fixes to save tokens and avoid HTML transcription errors. Edits are always published automatically.

Returns

publish_system

Publishes the current state of a system document by creating an immutable version snapshot. This captures the document’s content, description, notes, tags, videos, templates, and attachments at this point in time. Assigned users will see the published version. Optionally provide a version title/label (e.g. ‘v2.1 - Updated compliance section’). Each publish creates a new version; previous versions are preserved.

✅ What a restore actually brings back (our test, production, 25 Oct 2026). On a throwaway document: body, Overview (description), note and tags all came back, including removing a tag added after the snapshot. reviewDate did not and kept its current value — consistent with the list above, which never promises it. Videos, templates and attachments were not covered by that test. So publishing before a rewrite is a real safety net for content and metadata; set the review date again by hand after a restore. This replaces an earlier caveat of ours, based on a 9 Aug 2026 test of the older UI restore path, which said a restore returned only the body.

Returns

publish_policy

Publishes the current state of a policy document by creating an immutable version snapshot. This captures the document’s content, description, notes, tags, videos, templates, and attachments at this point in time. Assigned users will see the published version. Optionally provide a version title/label (e.g. ‘v2.1 - Updated compliance section’). Each publish creates a new version; previous versions are preserved.

✅ What a restore actually brings back (our test, production, 25 Oct 2026). On a throwaway document: body, Overview (description), note and tags all came back, including removing a tag added after the snapshot. reviewDate did not and kept its current value — consistent with the list above, which never promises it. Videos, templates and attachments were not covered by that test. So publishing before a rewrite is a real safety net for content and metadata; set the review date again by hand after a restore. This replaces an earlier caveat of ours, based on a 9 Aug 2026 test of the older UI restore path, which said a restore returned only the body.

Returns

publish_training

Publishes the current state of a training document by creating an immutable version snapshot. This captures the training’s content, description, notes, tags, videos, templates, and attachments at this point in time. Assigned users will see the published version. Optionally provide a version title/label (e.g. ‘v2.1 - Updated training content’). Each publish creates a new version; previous versions are preserved.

✅ What a restore actually brings back (our test, production, 25 Oct 2026). On a throwaway document: body, Overview (description), note and tags all came back, including removing a tag added after the snapshot. reviewDate did not and kept its current value — consistent with the list above, which never promises it. Videos, templates and attachments were not covered by that test. So publishing before a rewrite is a real safety net for content and metadata; set the review date again by hand after a restore. This replaces an earlier caveat of ours, based on a 9 Aug 2026 test of the older UI restore path, which said a restore returned only the body.

Returns

Version history

list_document_versions

Lists immutable published version snapshots for a system, policy, or training document, newest first. Each snapshot has a versionId, title, and createdAt. Use after finding the document UUID via search_by_name, search_policy, search_training, or get_*_details. Call this before restore_document_version to choose which snapshot to roll back to. Does not return version body content — restore to apply a snapshot to the live document. When presenting version history, list newest first. For each snapshot show title, createdAt, and versionId, and tell the user they must restore by versionId — never by date or timestamp. If the user names only a date, call list_document_versions, show matching rows with their versionIds, and ask which versionId to restore. Do not pick a snapshot from a date yourself. The latest row is the currently published snapshot assigned users see. Restore copies that snapshot onto the live document and publishes a new snapshot on top of history — then hard-refresh the document in SystemHub.

Returns

restore_document_version

Restores a previous published snapshot onto the live system, policy, or training document. Requires documentId and versionId. Ask the user for the versionId (a UUID from list_document_versions) — do not restore from a date, timestamp, or title, and do not guess which snapshot matches a date. If the user only names a date, list versions, show each versionId, and wait for them to pick one. Restore copies that snapshot’s content, description, notes, tags, videos, templates, and attachments onto the live document. Always publishes afterwards so the SystemHub UI (view mode) shows the rolled-back body — that creates a new snapshot on top of history; the restored versionId is unchanged. After restore, hard-refresh the document in the app.

Returns

Visual canvas

get_document_canvas

Reads the visual-builder canvas on a system, policy, or training document. Returns a compact flow graph (nodes with labels/shapes and directed edges) — not HTML content. Use this before editing a canvas, or to describe how an existing SOP/CCF diagram flows. Folders have no canvas. When hasCanvas is false, the document has no diagram yet. To create a new canvas, call set_document_canvas directly, then share the document reviewUrl so the user can verify it in the SystemHub web app.

Returns

set_document_canvas

Creates or replaces a visual-builder canvas on a system, policy, or training document. Call this directly when the user asks to create a canvas — do not wait for preview approval. Chat/PNG previews often do not match the SystemHub web builder. After saving, share reviewUrl and ask the user to open the document in the web app to review and edit the Canvas block. preview_document_canvas is optional only. A PNG is attached as an approximate image; do not paste base64. This replaces the entire canvas. Folders are rejected. Always published automatically. REQUIRED after saving: tell the user the canvas was written to the document, share reviewUrl (the SystemHub document link), and ask them to open it in the web app to review and adjust the Canvas block. Chat/PNG previews are approximate and often do not match how the diagram looks in SystemHub — the web editor is the source of truth. Do not paste previewPng, base64, or markdown images into the reply.

Returns

preview_document_canvas

Optional dry-run: previews a visual-builder canvas without writing it. Prefer set_document_canvas to create the canvas directly — do not require user approval from this preview, because PNG/chat previews often do not match the SystemHub web builder. Use this only if you want a quick approximate look before saving. Does not change the document. Folders are rejected. OPTIONAL helper only — do not block saving on this preview. A PNG is attached as an image; write a short explanation if useful. Do not paste previewMarkdown, data URIs, base64, mermaid, or SVG into the reply — Cursor shows those as code, not as a picture. PNG/chat previews often do not match the SystemHub web visual builder, so do not ask the user to approve from the preview alone. Prefer set_document_canvas to create the canvas, then give them reviewUrl to check and edit in the app. If replacesExistingCanvas is true, warn that saving will replace the current diagram.

Returns

clear_document_canvas

Removes the visual-builder canvas from a system, policy, or training document. The HTML body is left unchanged. After this, the SystemHub UI hides the Canvas block. Use set_document_canvas to create a new diagram. Always published automatically.

Returns

Organising

move_system

Moves a system document into a different system folder. Provide the document UUID and the destination folder UUID (use get_folder_tree to locate folders). The document stays a system. To move it into a policy or training folder, use move_document. Requires move permission on the document.

Returns

move_policy

Moves a policy document into a different policy folder. Provide the document UUID and the destination folder UUID (use get_policy_tree to locate folders). The document stays a policy. To move it into a system or training folder, use move_document. Requires move permission on the document.

Returns

move_training

Moves a training document into a different training folder. Provide the document UUID and the destination folder UUID (use get_training_tree to locate folders). The document stays a training. To move it into a system or policy folder, use move_document. Requires move permission on the document.

Returns

move_document

Moves a system, policy, or training document into a folder, including a folder in a different section. Same-section moves only change the folder. Cross-section moves convert the document (for example a system into a training folder) using the same rules as the web app. Moves into Training are allowed. Moving a training that has learning track steps out of Training returns a warning and keeps those steps on the document. If source does not match the document, the call fails and names the real section so you can retry. Use move_system, move_policy, or move_training when the document stays in the same section. Requires move permission on the document.

Returns

rename_system_folder

Renames a folder or sub-folder in the Systems section of SystemHub. Provide the folder UUID (from get_folder_tree) and the new title. Works at any depth in the folder tree. Requires folder rename permission.

Returns

rename_policy_folder

Renames a folder or sub-folder in the Policies section of SystemHub. Provide the folder UUID (from get_policy_tree) and the new title. Works at any depth in the folder tree. Requires folder rename permission.

Returns

rename_training_folder

Renames a folder or sub-folder in the Training section of SystemHub. Provide the folder UUID (from get_training_tree) and the new title. Works at any depth in the folder tree. Requires folder rename permission.

Returns

Templates, media, tags & comments

add_document_templates

Adds one or more document templates to a system, policy, or training document. Provide the document UUID (find it via search_policy, search_by_name, or search_training) and a list of templates. Each template requires title, subject, and details — ask the user for all three fields before calling this tool. Templates with a duplicate title on the same document are skipped. Always publishes the document after adding templates so they are visible outside edit mode.

Returns

edit_document_templates

Updates one or more existing document templates on a system, policy, or training document. Provide the document UUID (find it via search_policy, search_by_name, or search_training) and a list of edits. Each edit uses currentTitle to identify the template (case-insensitive) and at least one of title, subject, or details to change. Only provided fields are updated; omitted fields stay unchanged. Renaming to a title that already exists on the document is skipped. Always publishes the document after editing so changes are visible outside edit mode.

Returns

remove_document_templates

Removes one or more document templates from a system, policy, or training document by title. Provide the document UUID (find it via search_policy, search_by_name, or search_training) and a list of template titles to remove. Templates are matched by title (case-insensitive). Always publishes the document after removing templates so changes are visible outside edit mode. Returns which templates were removed and which titles were not found on the document.

Returns

add_document_videos_and_media

Adds one or more Videos & Media entries (media link URLs — videos, etc.) to a system, policy, or training document. Provide the document UUID (find it via search_policy, search_by_name, or search_training) and a list of entries. Each entry requires videoLink; title is optional. Entries with a duplicate link on the same document are skipped. Always publishes the document after adding so changes are visible outside edit mode.

Returns

remove_document_videos_and_media

Removes one or more Videos & Media entries (media link URLs — videos, etc.) from a system, policy, or training document. Provide the document UUID and identify entries by id (from videosAndMedia in get_details or search), title (case-insensitive), and/or videoLink (exact URL). Always publishes the document after removal so changes are visible outside edit mode. Returns which entries were removed and which were not found on the document.

Returns

add_document_tags

Adds one or more tags to a system, policy, or training document by title. Provide the document UUID (find it via search_policy, search_by_name, or search_training) and a list of tag titles. Existing tags are reused when the title matches, ignoring capitalisation. Unknown titles create new tags. Tags cannot be applied to folders. Always publishes the document after adding tags so they are visible outside edit mode (same as publish_policy/publish_system/publish_training). Returns which tags were added, which were already present, and the published version when applicable.

Returns

remove_document_tags

Removes one or more tags from a system, policy, or training document by title. Provide the document UUID (find it via search_policy, search_by_name, or search_training) and a list of tag titles to remove. This unlinks tags from the document only; the tag definitions remain available for other documents. Always publishes the document after removing tags so changes are visible outside edit mode. Returns which tags were removed and which were not on the document.

Returns

add_document_attachments

Uploads file attachments to a system, policy, or training document (max 100MB per file, up to 10 files per call). Supported formats: PDF (.pdf); Microsoft Word (.doc, .docx, .docm); Excel (.xls, .xlsx, .xlsm); PowerPoint (.ppt, .pptx, .pptm); plain text (.txt, .csv, .rtf); Markdown (.md). Max 100MB per file. Images, MP3, and MP4 must be uploaded in the systemHUB app. When the user attaches files in chat (Add files), read each file and pass contentBase64 + fileName — chat attachments are not sent to this tool automatically. Alternatively use fileUrl for a public download URL. Uploads are published automatically.

Returns

add_document_comment

Posts a new comment or reply on a system, policy, or training document. Provide the document UUID (find it via search_policy, search_by_name, or search_training) and the comment text. To reply to an existing thread, set parentCommentId to the parent comment UUID (find comment IDs in get_system_details, get_policy_details, or get_training_details). Optionally quote a document excerpt with matching topicType, or @-mention users via mentions (renders @-tags in the comment and sends mention notifications; unknown user IDs error). Notifications are also sent for new comments and replies. Retrying the same payload after a timeout returns the original comment instead of posting a duplicate.

Returns

Learning tracks

create_training_learning_track

Adds a learning track entry to a training document. A learning track links a specific base item as a required step in the training curriculum — always link a document (type=2), not a folder, so users can complete it and have their progress counted. Provide the training UUID, the base item UUID to link, and optionally a title and estimated completion time. Sort order is assigned automatically. Call publish_training after adding all entries to make the curriculum visible to assigned users.

Returns

edit_training_learning_track

Updates an existing learning track entry’s fields. Provide the training UUID, the learning track UUID, and any combination of fields to update: title, estimatedTime, or baseItem (UUID of the linked item). Only provided fields are changed; omitted fields remain untouched.

Returns

remove_training_learning_tracks

Removes one or more learning track curriculum steps from a training document. Provide the training UUID (find it via search_training or get_training_details) and identify steps by learningTrackIds (from learningTracks), titles (case-insensitive), and/or baseItems (linked document UUIDs). Always publishes the training after removal so changes are visible outside edit mode. Returns which steps were removed and which were not found.

Returns

Generated from the MCP schema snapshot. Refresh: re-dump data/mcp-schemas.json from the live connector, then run python3 scripts/generate_tool_reference.py. In the production pipeline this runs on every deploy.