Adobe Workfront

Use this for any request to set up, add, or change approvers or reviewers on a document — e.g. 'create an approval with X as approver', 'add a review stage'. This is the dedicated tool for document approval workflows. Create or update the approval workflow stages for a document version. Every stage must declare its prerequisites via `dependsOn` (use [] for the first stage / parallel roots). Most workflows are LINEAR: stages[0].dependsOn=[], stages[1].dependsOn=[0], stages[2].dependsOn=[1], and so on. Use a graph (parallel branches, fan-in) only when the workflow genuinely requires it. Provide all desired stages — this replaces or extends the existing workflow. On clients that support MCP Apps, a visual preview is shown for confirmation. On clients that support elicitation but not apps, the user is asked to confirm inline. Otherwise the change is applied directly.

approvals_create_or_update_approval_workflow

Create one or more record types. A default table view is created automatically for each; do not create another unless the user explicitly wants multiple table views. PREREQUISITE: The workspace must have a section — call update_workspace to add one if needed. Read docs://workspace-setup-guide for best practices on record type design, field configuration, and connection patterns. isGlobal=true requires admin privileges (check is_admin in user_info); default to local record types. Not atomic — check the hasErrors flag in the response. Per-item results show success/failure with error details. When tool B needs an ID returned by tool A, call them in SEPARATE turns. Wait for A's response, then use the actual returned ID in B. Hierarchy: Workspace → Section → RecordType → Field/View/Record.

planning_create_record_types

Create a reply to an existing comment. Supports rich text, HTML content, tags, and attachments. IMPORTANT: 1) When tagging users or teams, you MUST use the "tags" array with objects shaped as: { id: string, objCode: "USER" | "TEAMOB" }. For users, ALWAYS use the Workfront wfId (32-character hex string). 2) Use dry_run: true first to preview the reply and confirm it is correct before posting. A dry run returns the validated payload and NEVER sends any notifications. RECORD objects (objectCode: "RECORD"): the response will NOT include a `links` field for RECORD objects. Construct the URL client-side using this format: - Updates/details page: {host}/maestro/{workspaceID}/{recordTypeID}/{recordID}/record/details - Specific comment: {host}/maestro/{workspaceID}/{recordTypeID}/{recordID}/record?commentID={commentID} Use the comment's `_id` for {commentID}. Resolve {workspaceID} and {recordTypeID} by calling the maestro lookup tools available in your session (look up by recordID = the comment's `objectID`). {host} matches the host used to invoke this MCP server.

comment-stream_create_reply

Create a new view for a record type. Views define how records are displayed: table (spreadsheet), timeline (Gantt chart), or calendar. Can configure filters, sorting, and grouping during creation. Read docs://view-types for view type requirements and capabilities. For filter configuration, read docs://filter-operators for supported operators by field type. When tool B needs an ID returned by tool A, call them in SEPARATE turns. Wait for A's response, then use the actual returned ID in B. Hierarchy: Workspace → Section → RecordType → Field/View/Record.

planning_create_view

Create a new empty workspace. A workspace is a container for organizing related record types, fields, and data. Read docs://workspace-setup-guide for best practices on workspace structure, naming conventions, and section organization. When tool B needs an ID returned by tool A, call them in SEPARATE turns. Wait for A's response, then use the actual returned ID in B. Hierarchy: Workspace → Section → RecordType → Field/View/Record.

planning_create_workspace

Create a new workspace from a template. The template provides pre-configured record types, fields, views, and sample data. Use get_template_list to find available templates and get_template for full template details. Optionally override the workspace name, description, icon, and alias after creation from the template.

planning_create_workspace_from_template

Delete a single stage from an approval workflow by name or position (e.g. 'Legal Review', 'stage 2', 'last stage'). Only not-started stages can be deleted. For approvals with parallel paths, use remove_stage_from_path instead — this tool only works on single-path approvals.

approvals_delete_approval_stage

Delete a comment by its ID. Marks the comment as deleted and updates the deleted metadata. Users can only delete their own comments or must have admin privileges. RECORD objects (objectCode: "RECORD"): the response will NOT include a `links` field for RECORD objects. Construct the URL client-side using this format: - Updates/details page: {host}/maestro/{workspaceID}/{recordTypeID}/{recordID}/record/details - Specific comment: {host}/maestro/{workspaceID}/{recordTypeID}/{recordID}/record?commentID={commentID} Use the comment's `_id` for {commentID}. Resolve {workspaceID} and {recordTypeID} by calling the maestro lookup tools available in your session (look up by recordID = the comment's `objectID`). {host} matches the host used to invoke this MCP server.

comment-stream_delete_comment

Delete a Field by ID. This permanently removes the field from its record type, including all data stored in this field across all records. This action cannot be undone. The field must exist and the user must have EDIT permission on the record type.

planning_delete_field

Delete a Workfront object by ID. Supported types: projects, tasks, issues/requests, portfolios, programs, hour entries, assignments, plus users, teams, roles, and groups (admin only). - MUST obtain explicit user confirmation (object type, ID, and name) before invoking. If the user's CURRENT message already contains explicit confirmation language ("yes, delete it", "I'm sure, delete X", "confirm delete"), proceed without re-prompting — do NOT ask again. Only ask if the message merely describes the deletion without confirmation. - When the user identifies the target by name, FIRST call insights_find_id_by_name (entity = the objectType) to obtain its ID, THEN call delete_any_object in the same turn — do not stop after the lookup. If the result is ambiguous, ask the user to choose from the returned options instead of guessing. - 'force: true' bypasses the Recycle Bin and is permanent; warn the user and require a second confirmation before passing it. - You MUST call read_workflow_docs with workfront://tools/delete-any-object BEFORE this tool whenever the request involves a status/enum value, a filter modifier other than plain equality (_Mod/_Range), a date comparison, a scheduling or date field on a project or task (scheduleMode, taskConstraint, plannedStartDate, plannedCompletionDate, constraintDate), a task dependency field (predecessorExpression), a relation path (a field containing ":"), result ordering (orderBy), or a force delete. Skip it only for a confirmed, non-force delete after a pure identity equality lookup. OUT OF SCOPE for these any-object tools — do not attempt, do not imply success: - Uploading or attaching a document - Posting a comment or replying to a comment thread - Creating or advancing an approval/review step - Setting or comparing a project baseline - Logging or approving an expense - Creating a milestone (or milestone path) - Adding a note - Restoring an object from the Recycle Bin For any of these, check whether a dedicated tool for that action is available before falling back to the object's Workfront UI page (the `url` field on a returned object, or https://<host>/<urlSegment>/<objectID>).

workflow_delete_any_object

Delete a Record Type by ID. This will permanently remove the record type and ALL its data including all records, fields, and views. Requires MANAGE permission. WARNING: This action cannot be undone. All records of this type will be permanently deleted.

planning_delete_record_type

Delete a view by ID. This permanently removes the view configuration but does NOT delete records. Requires MANAGE permission. Cannot be undone. The last table view in a record type cannot be deleted.

planning_delete_view

Delete a workspace by ID. Permanently removes the workspace and all its data. Requires MANAGE permission. Use workspace ID only (not name/alias); use get_workspace_list to find the ID if needed.

planning_delete_workspace

Look up a document by filename OR by document version ID (DOCV) — provide exactly one. Use document_name when the user names a file ("winter-campaign.pdf"); use document_version_id when you have a DOCV from a Workfront URL or another tool. Returns document name and current version ID (for name search) or full metadata (for version ID lookup). Matching by name is word-order-tolerant: 'pink whale' matches 'Whale-pink'. Behavior: single match → use it; multiple matches → return all and ask the user to pick; zero matches → tell the user the file was not found.

approvals_find_document

Find and resolve a named Workfront object — project, task, issue, user, portfolio, program, team, document — to its GUID for use in a filter condition.

insights_find_id_by_name

Use this to answer questions like "show me my tasks", "what's due this week", "list open projects", "find tasks assigned to me", "how many issues are overdue", "which projects are behind schedule", "count tasks by status", "show unassigned tasks", "get planned hours for a project", "find issues submitted this month", "what project templates are available". This is the primary read/query tool for all Workfront data retrieval. REQUIRED: call read_docs("mcp-usage") first if you have not already done so this session. Search, list, filter, count, sort, or retrieve Workfront data — projects, tasks, issues, users, portfolios, programs, teams, documents, milestones; returns rows, columns, totalCount.

insights_find_workfront_data

Look up Workfront projects, optionally filtered by name and/or restricted to projects the calling user owns. Use a name fragment when the user names a project ("Winter Campaign", "Q4 Launch"); set owned_by_me when the user says "my projects", "projects I own", or "what am I working on". Behavior: owned_by_me alone → projects the user owns; name alone → matching projects across the system; both → owned projects whose name matches. Returns project name, ID, and status for each match — feed a project ID to get_documents_by_scope, then approval tools on the documents. Multiple matches → return a numbered list and ask the user to disambiguate; zero matches → tell the user.

approvals_find_projects

Look up a Workfront team's ID by name (fuzzy/partial match). Call this whenever the user wants a whole team — not a single person — as an approver or reviewer ("send to the Design team", "Legal team should approve"). Approval and template tools accept teams as participants with participantType: "TEAMOB" and the ID this tool returns. Behavior: single match → use it; multiple matches → return a numbered list and ask the user to pick; zero matches → tell the user no team was found. The word "team" is stripped from the query automatically.

approvals_find_team_by_name

Look up a Workfront user's ID by name (fuzzy/partial match). Call this whenever the user mentions a person by name ("add Deepak as reviewer", "send to Sarah for approval") — downstream tools like create_or_update_approval_workflow, create_template, and send_approval_reminder all require Workfront user IDs, not names. Use this for any approval-participant resolution (approver, reviewer, requester); it is approval-aware and returns the fields downstream approval tools need. Returns name, ID, email, title, and avatar URL. Behavior: single match → use it directly; multiple matches → return a numbered list, surface the options to the user and let them disambiguate; zero matches → tell the user no match was found and ask for a different spelling. Do not silently retry with a different name.

approvals_find_user_by_name

Get the current approval workflow (stages, participants, status, stage IDs) for a document version. REQUIRED before sending reminders or modifying an existing approval — returns the stage IDs that send_approval_reminder and delete_approval_stage need. This is the canonical way to read approval state for a document.

approvals_get_approval_info

Get a single comment by its ID. Returns detailed information about a specific comment. RECORD objects (objectCode: "RECORD"): the response will NOT include a `links` field for RECORD objects. Construct the URL client-side using this format: - Updates/details page: {host}/maestro/{workspaceID}/{recordTypeID}/{recordID}/record/details - Specific comment: {host}/maestro/{workspaceID}/{recordTypeID}/{recordID}/record?commentID={commentID} Use the comment's `_id` for {commentID}. Resolve {workspaceID} and {recordTypeID} by calling the maestro lookup tools available in your session (look up by recordID = the comment's `objectID`). {host} matches the host used to invoke this MCP server.

comment-stream_get_comment

Get the total count of top-level comments for a specific object, matching what `query_comments` would return across all pages. For container objects (e.g. PROJECT), the count includes comments on child objects (e.g. tasks, issues) the same way the listing tool does. Replies are not included in the count; they are nested under their parent comment in `query_comments`. RECORD objects (objectCode: "RECORD"): the response will NOT include a `links` field for RECORD objects. Construct the URL client-side using this format: - Updates/details page: {host}/maestro/{workspaceID}/{recordTypeID}/{recordID}/record/details - Specific comment: {host}/maestro/{workspaceID}/{recordTypeID}/{recordID}/record?commentID={commentID} Use the comment's `_id` for {commentID}. Resolve {workspaceID} and {recordTypeID} by calling the maestro lookup tools available in your session (look up by recordID = the comment's `objectID`). {host} matches the host used to invoke this MCP server.

comment-stream_get_comments_count

Find and retrieve the current user's Workfront identity (name, ID, URL) for personalizing a response. When to call: when the response should address the user by name or include a direct link to a Workfront object that needs the user's workfront URL as a base. Do NOT call this just because the question mentions "me" / "my" / "mine" — use the `$$USER.ID` sentinel directly inside conditions instead. This tool is for rendering a response, not for filtering. Returns: ok with {user_id, user_name, wf_url}.

insights_get_current_user

Get the calling user's Workfront identity: name, user ID, home team name, and home team ID. Use when the user refers to themselves ("me", "my projects", "approvals I own") and you need a concrete ID, or before any tool that needs to attribute action to the current user. Returns a single user every call — no disambiguation needed. Do not call this just to learn who the user is at the start of a conversation; only call it when an ID is actually required.

approvals_get_current_user

List documents (with name and current version ID) inside a project or folder. Call this when the user wants to act on documents in a project or folder ("start approval on every file in the Winter Campaign project", "what's in the Final folder"). Pick the scope_type that matches the user's intent: - "project" → scope_id = project ID. Returns all documents in that project. - "folder" → scope_id = folder ID directly. Returns documents in that specific folder. - "folder_name" → scope_id = project ID, plus folder_name. Resolves the named folder within the project, then returns its documents. Returns a numbered list of documents with name and document version ID (DOCV). Feed the version IDs to approval / AEM / reminder tools. If folder_name matches multiple folders, the tool returns the folder options instead — re-call with scope_type=folder and the specific folder ID.

approvals_get_documents_by_scope

Find which Maestro workspaces and record types are connected to a specific external object. Use this to check whether an external record (e.g. a Workfront project) is already linked to a Maestro record, or to discover which workspaces/record types can accept a connection for that object type. Returns a list of entries, each containing the Maestro record linked to the external object and the workspace it lives in. See docs://connections for available connections and their supported object types.

planning_get_external_record_workspaces

Get Field details by ID. Returns field configuration and a fieldValueSchema describing how to format values for this field when creating or updating records. TIP: To see all fields on a record type at once, prefer get_record_type with attributes=['id','displayName','fields'].

planning_get_field

Resolve and retrieve dot-notation field paths for Workfront entities — projects, tasks, issues, users, portfolios, programs, teams — required by find_workfront_data(). Returns the single best root entity and, per field, all candidate paths.

insights_get_field_paths

Get Record details by ID. Returns all attributes.

planning_get_record

Get field change history for a record. Returns chronological list of field value changes (most recent first) showing what changed, when, and by whom. Includes both before/after values for each change. Useful for audit trails and tracking record modifications. Excludes system field changes. Supports pagination via offset/limit.

planning_get_record_change_log

Get record sharing. Retrieves sharing/permissions information for a specific record, including who has access and their permission levels. Returns a wildcard access level (EVERYONE_IN_WORKSPACE or SELECTED_USERS_ONLY) and a list of sharing entries. Requires MANAGE permission on the record type containing the record.

planning_get_record_sharing

Get Record Type details by ID. Retrieves complete information about a specific record type including its configuration, fields, permissions, metadata, and a summary of all views (table/timeline/calendar). For global record types (isGlobal=true), also includes global settings such as which workspaces use it and authorization config (requires MANAGE permission). For per-field value schemas (field IDs, types, formats), read the schema://record-type/{recordTypeId} resource.

planning_get_record_type

Get record type sharing. Retrieves sharing/permissions information for a record type, including who has access and their permission levels. Returns list of objects containing users, groups, teams, roles, and companies with their assigned permissions. Requires MANAGE permission on the workspace containing the record type. For dynamic (global) record types, use scopeWorkspaceId to get workspace-specific sharing.

planning_get_record_type_sharing

Get template details by template ID, projected at the requested detail level. Use 'minimal' for just identity and counts, 'metadata' (default) for the embedded workspace with record-type metadata but no fields, or 'full' for the complete legacy payload (workspace + all fields + views + default records + layouts + pages + business rules + hierarchies).

planning_get_template

List all available templates with lightweight summary info (ID, name, description, type, icon). Use get_template with the template ID to retrieve full details.

planning_get_template_list

Get complete view details by ID. Returns view configuration including name, type (table/timeline/calendar), metadata (date fields, column settings), filters, sorting, grouping, permission level, sharing status, and audit fields. Use this to inspect view settings or retrieve date field IDs.

planning_get_view

Get view sharing. Retrieves sharing/permissions information for a view, including who has access and the view's public sharing status. Returns object with view ID, token info (public sharing details), and sharing list (users, groups, teams with their permission levels). Requires MANAGE permission on the view.

planning_get_view_sharing

Get workspace details by ID or alias. Returns workspace metadata, sections, and a list of record types projected at the requested detail level (defaults to 'metadata' — every record type's attributes EXCEPT its full field definitions, with a fieldCount instead). Use 'minimal' for the smallest payload (id/alias/displayName/permission/flags only) or 'full' to inline every field — note 'full' can produce multi-MB responses for schema-heavy workspaces and should be used sparingly. For full field definitions of a specific record type, call get_record_type.

planning_get_workspace

Get workspaces with cursor-based pagination. Returns a lightweight summary for each workspace (id, name, description, permission, createdBy/At, updatedBy/At). Use get_workspace with a specific workspace ID to retrieve workspace metadata, sections, and record-type summaries; call get_record_type to drill into a record type's fields.

planning_get_workspace_list

Get workspace sharing. Retrieves sharing/permissions information for a workspace, including who has access and their permission levels. Returns list of objects containing users, groups, teams, roles, and companies with their assigned permissions. Requires MANAGE permission on the workspace.

planning_get_workspace_sharing