OrgX MCP - Agent Orchestration

Representative rich result

Representative exact result

Get an organization-wide execution snapshot across initiatives, work, blockers, and context. Also known as: org status, team overview, company memory. USE WHEN: user wants an org-wide overview of initiatives, progress, and health. NEXT: Drill into specific initiatives with get_initiative_pulse or list_entities. DO NOT USE: for a single initiative — use get_initiative_pulse instead. Read-only.

Get the current OrgX account tier, billing status, and usage snapshot for the authenticated user.

Create the next-step upgrade or agent credit top-up flow for the authenticated OrgX account. Enterprise requests return contact guidance instead of self-serve checkout.

Get a detailed usage and billing report for the authenticated OrgX account, including quotas, period boundaries, and overage signals.

List projects, tasks, milestones, decisions, agents, artifacts, and other OrgX records with filtering. Also known as: browse work, find entities, search project records. Returns FULL UUIDs usable with entity_action/batch_action. Use fields=["id","title","status"] for compact output when you only need IDs. Supported types: ${ENTITY_TYPES.join( ', ' )}. USE WHEN: browsing, searching, or getting entity IDs for bulk operations. NEXT: For initiatives, suggest get_initiative_pulse for health. For tasks, suggest entity_action to change status. For full context on one entity, add hydrate_context=true with id. DO NOT USE: for org-wide overview — use get_org_snapshot instead. Read-only.

Change work state, attach artifacts, or run lifecycle actions on OrgX records. Also known as: launch, pause, complete, attach proof, update status. Accepts short ID prefix (8+ hex chars) — no need to look up full UUIDs. USE WHEN: user wants to change entity status. For bulk operations (pausing multiple, completing multiple), use batch_action instead. Supports aliases: launch, pause, complete (resolved per type). Omit action to list available actions. Special actions: attach (create an artifact linked to the entity), complete_with_proof (attach proof, verify, then complete in one call), ship_batch (milestones only — atomically attach one artifact + mark multiple subcomponent tasks complete when a single PR covers them all). NEXT: After completing, call verify_entity_completion first to check child work is done. DO NOT USE: for creating entities — use create_entity or scaffold_initiative.

Run pre-completion verification to confirm all child work is done. For tasks, this also checks proof-chain hard blocks that would stop entity_action action=complete. USE WHEN: before completing an entity with entity_action action=complete. NEXT: If verified, proceed with entity_action action=complete. If not, show blockers to user. Read-only.

Create durable work records such as tasks, milestones, decisions, artifacts, or initiatives. Also known as: save work item, add record, create project context. USE WHEN: adding a single task, milestone, workstream, or other entity to an existing hierarchy. NEXT: Use entity_action to launch/start the entity. DO NOT USE: for creating a full initiative hierarchy — use scaffold_initiative instead.

Leave a threaded comment on an entity. USE WHEN: agent or user wants to annotate an entity with observations, concerns, or progress notes. NEXT: Use list_entity_comments to read the thread. DO NOT USE: for status changes — use entity_action instead.

List comments for an entity. USE WHEN: reviewing discussion thread on an entity. NEXT: Use comment_on_entity to add a reply. Read-only.

Create multiple entities in one call with ref-based dependency resolution. USE WHEN: creating several related entities at once. NEXT: Use entity_action to launch created entities. DO NOT USE: for initiative hierarchies — use scaffold_initiative which handles the nesting automatically.

Fetch a task with hydrated context attachments (entities, artifacts, plan sessions). USE WHEN: agent needs full task context before executing, or user wants task details. NEXT: Use entity_action to update task status. DO NOT USE: for listing tasks — use list_entities type=task instead.

Delete multiple entities in one call (hard delete). USE WHEN: user explicitly wants to remove entities permanently. NEXT: Verify deletion succeeded. DO NOT USE: for archiving or pausing — use entity_action instead.

Execute actions on multiple entities in one call (pause, launch, complete, resume, etc.). USE WHEN: bulk state changes like pausing multiple initiatives or completing multiple tasks. ACCEPTS: short ID prefixes (8+ chars) — no need to look up full UUIDs. Supports the same launch/pause aliases as entity_action. NEXT: Verify all actions succeeded. DO NOT USE: for deletes — use batch_delete_entities instead.

Update an existing entity. Only include fields you want to change. USE WHEN: modifying entity fields (title, description, priority, etc.). NEXT: Confirm changes to user. DO NOT USE: for status changes — use entity_action instead.

Check setup status, configure agents, or set org policies. action=status for progress, action=configure_agent to set agent preferences, action=set_policy for org-wide rules.

Get productivity stats, achievements, and streaks. scope=personal for your stats, scope=session for current session diagnostics. Read-only.

Create, list, get, or set the active workspace. action=create creates a workspace and makes it active by default; action=list shows all; action=get returns current; action=set switches active.

Create or approve a workspace outcome type before recording custom baseline, audit, or quality-gate outcomes.

Create or approve a workspace outcome type before recording custom baseline, audit, or quality-gate outcomes.

Record a business outcome. Triggers attribution inference to connect outcomes to receipts. If the outcome type is unknown, call configure_outcome_type first.

Resume a paused or auto-closed agent run. Flips status back to running, clears TTL auto-close markers, and appends a resume_history entry. USE WHEN: the user wants to continue a reporting session that was auto-closed by the stale-TTL cron, or reactivate any paused run. DO NOT USE: to restart a completed/failed/cancelled run — those are terminal.

Agent-facing: trust level per capability, promotion requirements, receipt evidence. Returns full trust context for self-awareness.

Run a free autonomy benchmark from trust, proof, ROI, and workspace signals. Returns Proof Score, Context Debt, Autonomy Maturity, ROI Visibility, and next recommendations without starting an autonomous session or consuming agent credits.

Start an autonomous execution session with budget guardrails. Creates a session that produces receipts while executing eligible work.

Agent-facing: organizational learnings relevant to a capability or task context. One agent\'s discovery benefits all agents.

Agent-facing: submit a discovery as an org learning. Enters org_learnings after confidence validation.

DEPRECATED: Use entity_action action=attach instead. This tool still works as a thin compatibility wrapper that attaches an artifact to a task, milestone, initiative, workstream, project, or decision. USE WHEN: legacy clients still call save_artifact. NEXT: Prefer entity_action action=attach for new code — it exposes the full attachment surface (preview_markdown, status, metadata, created_by_*). DO NOT USE: for generic entity creation — use create_entity instead.