OrgX

By useorgxMCP server

OrgX is coordination infrastructure for AI-native teams. It gives your LLM a persistent organizational layer: initiatives with milestones and tasks, human-in-the-loop decision workflows, specialist agent delegation, and cross-session memory that survives tool switching. What you can do with OrgX via MCP: Scaffold initiatives — decompose a goal into workstreams, milestones, and tasks in one call Manage decisions — create, review, approve, or reject decisions with audit trails Delegate to specialist agents — spawn tasks for domain agents (engineering, marketing, product, sales, operations, desi

SEO & MarketingLibrary synced Nov 6, 2026

https://mcp.useorgx.com/

Follow the source guide for connection and authentication details.

Available tools

approve_decision

Use when the user has reviewed a pending decision that is blocking agent work and gives explicit confirmation to approve it. Also known as: sign off, approve AI work, unblock agent, accept decision. USE WHEN: user says to approve a decision returned from list_entities with type=decision and status=pending (or the legacy get_pending_decisions alias). NEXT: Confirm approval to user; agent is notified automatically. DO NOT USE: without showing the decision to the user first. Requires decisions:write.

reject_decision

Use when the user has reviewed a pending decision and wants to reject it or send the agent back with revisions. Also known as: request revisions, send feedback, decline decision. USE WHEN: user wants to reject or request revisions on a decision. NEXT: Agent will revise their approach based on the reason. DO NOT USE: without a reason — always include why. Requires decisions:write.

get_agent_status

Use when the user asks what agents are working on right now, whether delegated work is still running, or why nothing has landed yet. Also known as: agent status, what agents are doing, active runs. USE WHEN: user asks about agent activity, progress, or what agents are working on. NEXT: If agents are stuck, suggest approve_decision or entity_action. DO NOT USE: to check initiative health — use get_initiative_pulse instead. Read-only.

query_org_memory

Use when context was lost between sessions, another agent's work must be continued, or the answer may already exist in team memory. Also known as: search memory, recall decisions, find context, retrieve artifacts, project memory. USE WHEN: user asks about past decisions, context, or knowledge. NEXT: Present relevant results; suggest drill-down with list_entities. Prefer `query_org_memory` with scope=decisions with a topic query for new prompts, skills, and examples. DO NOT USE: for listing current entities — use list_entities instead. Read-only.

get_initiative_pulse

Use when the user asks how a project is going, what is blocked, or whether an initiative is on track. Also known as: project status, roadmap progress, execution health, blockers. USE WHEN: user asks how an initiative is going, or wants a status update. NEXT: If blockers exist, suggest entity_action to resolve. For deeper drill-down, use list_entities with initiative_id. DO NOT USE: for org-wide overview — use get_org_snapshot instead. Read-only.

spawn_agent_task

Use when the user says "delegate this and tell me when it's done" — assign work to a specialist AI agent that owns the task and reports back with results. Also known as: hand this off, assign task, spawn agent, have an agent do it, autonomous work. Automatically checks authorization, rate limits, quality gates, model routing, and budget policy before spawning. Omit model_tier/provider/model to let OrgX auto-route from task complexity; provide them only when the user or verification plan intentionally constrains routing. Returns modelTier, budget, and run details on success, or blockedReason if spawn is denied. USE WHEN: user explicitly wants to delegate work to an agent. NEXT: Use get_agent_status to monitor progress and record_quality_score after reviewing output. DO NOT USE: for creating tasks in the hierarchy — use create_entity type=task instead. Requires agents:write.

handoff_task

Use when in-flight work must move to a different specialist agent without losing its context or execution state. Also known as: handoff task, transfer work, change assignee. USE WHEN: a task needs to be reassigned to a different specialist agent. NEXT: Use get_agent_status to confirm the new agent picked up the task. DO NOT USE: for new tasks — use spawn_agent_task instead.

recommend_next_action

Use this tool to recommend what should happen next after time away or when priority is unclear. It ranks progress gaps, blockers, and execution templates. Pass agent_id or domain for an agent-owned runnable queue instead of the workspace-wide operator queue. Also known as: next best action, prioritize work, unblock project. USE WHEN: the user asks what to do next or needs help prioritizing. NEXT: Execute the recommended action (entity_action, spawn_agent_task, etc.). DO NOT USE: when the user already knows what they want to do. Read-only.

manage_lifecycle

Pause, resume, retry, or cancel any node in the work hierarchy — an initiative, workstream, milestone, task, or run. Propagates to descendant tasks + active runs. USE WHEN: the user wants to halt, restart, or re-run part of an initiative. resume/retry re-dispatch the work; pause/cancel stop active runs. NEXT: get_initiative_pulse to confirm. DO NOT USE: to mark a task done — use entity_action instead.

get_operator_chronicle

Use when the user asks what happened, wants to catch up after time away, or needs a reporting window summarized with decisions and proof. Read the operator chronicle: decision chronology, yesterday/week/30-day rollups, reportingNarrative.briefMarkdown, artifacts, PR receipts, active initiatives, goals, top priorities, velocity, and reporting gaps for a workspace. USE WHEN: user asks what changed yesterday, this week, or this month; asks for decision chronology, top priorities, PR velocity, artifacts, goals, or what OrgX is missing. NEXT: present reportingNarrative.briefMarkdown first, then use reportingNarrative.nextAction and topPriorities for drill-down. Read-only.

check_execution_readiness

Check whether the workspace has the credentials needed to dispatch agent work, BEFORE spawning. USE WHEN: about to call orgx_spawn / spawn_agent_task and you want to confirm execution credentials exist — avoids dispatching a run that fails on missing keys. NEXT: if not ready, surface what is missing and resolve it; if ready, proceed to orgx_spawn. Read-only; dispatches nothing.

orgx_emit_activity

Use when an agent is mid-execution and its progress must stay visible to operators and to the next agent that resumes the run. Emit append-only run telemetry for OrgX control-plane reporting. USE WHEN: agent is executing and needs to report progress. NEXT: Continue work; emit again at each phase change. DO NOT USE: for entity status changes — use entity_action instead. Setting phase="completed" records telemetry only and does not mark tasks, workstreams, or initiatives complete.

orgx_request_attention

Forward a typed human-interruption request while preserving the originating run and session. Use kind=question for missing context, permission for a scoped tool or file action, approval for owner sign-off, and recovery only when automatic retry cannot safely continue. USE WHEN: a native client reaches a genuine human decision that prevents the preserved session from continuing safely. NEXT: poll orgx_poll_attention; resume only after the answer is applied, then call orgx_ack_attention so Live can show that work actually restarted. DO NOT USE: for internal turn boundaries or retryable runtime events.

orgx_poll_attention

Read the durable owner response and continuation state for orgx_request_attention. USE WHEN: the client has a preserved attention_id and must determine whether the owner answered without creating another request. When resolved=true, apply the answer to the preserved session. NEXT: call orgx_ack_attention with state=resuming, then state=resumed only after native execution actually restarts. Read-only.

orgx_ack_attention

Report what happened after an owner answered an attention request. Use answer_received when stored locally, resuming when native continuation begins, resumed only after work emits again, resume_failed with an actionable detail when it cannot restart, or cancelled when intentionally stopped. USE WHEN: the source client has objective evidence for a continuation state transition. NEXT: keep the same attention_id and idempotency key through terminal resumed, resume_failed, or cancelled state. DO NOT USE: to infer that work resumed merely because the decision was resolved; wait for native execution evidence. This receipt prevents Live from claiming work is moving before the source client confirms it.

orgx_request_question

Pause at a safe checkpoint and forward a contextual question to the initiative owner. OrgX renders the right single-select, multi-select, free-text, or confirmation control and preserves the source run/session so work can resume with the exact answer. USE WHEN: Claude Code AskUserQuestion, Codex request_user_input, Cursor, OpenClaw, or another client needs human judgment to continue. NEXT: poll orgx_poll_question with the returned question_id; continue only when continuation.should_resume is true. DO NOT USE: for runtime failures with an automatic retry path — report a chokepoint instead.

orgx_poll_question

Read the durable answer receipt for a question previously forwarded with orgx_request_question. USE WHEN: an external client is paused for human input. NEXT: when resolved=true and continuation.should_resume=true, resume the preserved source session with answer and resolution_context; when false, remain paused without creating another question. Read-only.

orgx_emit_execution_graph

Emit the deterministic execution graph + trust ledger for the active run: nodes (claimed status + verification evidence), depends_on edges, and trust events. OrgX derives false-completion, hallucinated-receipt, and dependency-violation signals from this and surfaces them on /live. USE WHEN: reporting the structured shape of multi-step work — NOT a single progress line (use orgx_emit_activity for that). NEXT: continue work; re-emit as the graph advances (idempotent per run + graph fingerprint). DO NOT USE to mark entities complete — telemetry only.

consolidate_pr

Use when the user or an engineering agent must show a pull request actually shipped and needs durable review proof, not a status glance. Generate and persist an orchestration.consolidation_pass receipt for a GitHub pull request. Requires OrgX server-side GitHub credentials; if the GitHub token is unavailable, use GitHub tools for PR facts and return a structured blocker instead of retrying. USE WHEN: Eli or another engineering agent needs a durable PR review receipt with reading order, existence evidence, deduped findings, verdict, and server-derived AQ score. NEXT: inspect the returned artifact_id or attach it to task completion proof. DO NOT USE WHEN: only asking for PR status; use GitHub tools instead.

orgx_bootstrap

Use at the start of a fresh session, after reconnecting, or before continuing work another agent left behind. Establishes OrgX session context, discovers granted scopes, and returns the v2 tool routing map. Also known as: bootstrap, setup, tool routing. USE WHEN: first call in a fresh session, after reconnecting, or before performing a multi-step workflow. NEXT: use orgx_search, orgx_inspect, or orgx_recommend based on the returned routing map. DO NOT USE WHEN: you already have session context and need to read or mutate work. Read-only.

orgx_inspect

Use when the user names a specific task, milestone, initiative, decision, artifact, or plan session and you need its real state — decisions, owners, linked proof — before acting. Hydrates one OrgX entity with execution context. Also known as: Inspect OrgX Entity, inspect initiative, get full entity context. USE WHEN: continuing work on a named entity or verifying state before a lifecycle change. NEXT: use orgx_act, orgx_attach, or orgx_write if the user asks to change what you inspected. DO NOT USE WHEN: browsing or searching many records; use orgx_search. Read-only.

orgx_search

Use when context was lost between sessions, another agent's work must be continued, or the answer may already exist in team memory. Finds OrgX entities, decisions, artifacts, and memory. A query without type runs a mixed relevance search; typed searches provide exhaustive cursor/offset pagination. Also known as: Search OrgX, find initiative ID, list work, browse OrgX. USE WHEN: browsing work, searching memory, finding IDs, or listing related records. NEXT: use structuredContent.next_call exactly when pagination.has_more=true, orgx_inspect for one selected result, or orgx_recommend when the user asks what to do next. DO NOT USE WHEN: you already know the exact entity and need full context; use orgx_inspect.

orgx_recommend

Use when the user asks what to do next, wants a brief, or returns after time away and needs priorities. Recommends next work, summarizes operator-chronicle/morning-brief signals, and reads prioritization context. USE WHEN: user asks what to do next, wants a brief, asks what changed yesterday/week/30 days, or needs priority guidance. mode=morning_brief returns the operator chronicle when available. NEXT: present the recommendation, then use orgx_act, orgx_write, or orgx_spawn only after the user confirms an action. DO NOT USE WHEN: the user already specified the action; use orgx_act or orgx_write.

orgx_write

Create or update one OrgX record (snake_case fields). Operations: create (default) uses per-type fields; update REQUIRES id + fields. Create requirements: workspace name/title; initiative title/name + workspace_id + goal_ids when the workspace enforces primary objectives; workstream title + initiative_id; milestone title + workstream_id; task title + workstream_id + milestone_id when the workspace requires backlog milestones; decision title; artifact target + artifact_type + artifact_url/external_url; blocker run_id + metadata.description; skill/studio records title. Retry behavior: pass idempotency_key on creates. A key match returns the same UUID as an idempotent replay, without creating a duplicate. Initiative gotchas: priority only accepts low|medium|high|urgent, not portfolio labels such as active/critical/maintenance/hold; put portfolio urgency in metadata/priority_rank. due_date is not accepted on initiative create in current workspaces; put target dates in metadata until a typed initiative schedule field exists. USE WHEN: adding/editing records. NEXT: orgx_act to launch/complete the record. DO NOT USE for lifecycle changes — use orgx_act or orgx_attach.

orgx_attach

Use when work produced a deliverable that needs provenance and review — attach the artifact or proof URL to an OrgX entity. Requires artifact_url or external_url; preview_markdown is supporting context only. USE WHEN: saving evidence, PRs, documents, reports, screenshots, or external artifacts. For founder/team work, prefer practical artifact_type codes such as orchestration.next_initiative, eng.pull_request, eng.deploy_proof, eng.structured_blocker, sales.strategy, sales.icp_offer_sequence, sales.send_plan, sales.conversion_gates, marketing.launch_asset, marketing.channel_hypothesis, marketing.positioning_brief, marketing.proof_distribution_plan, marketing.interview_pr_plan, product.customer_discovery, product.prd, product.pricing_hypothesis, product.decision_record, design.audit, design.component_spec, design.token_package, ops.operator_brief, ops.runbook, ops.budget_envelope, ops.incident_status, proof.link. Include business_outcome, owner/review_date, and verification when the artifact should close agent work. NEXT: use orgx_submit_receipt to close attribution/quality loops or orgx_act to complete with proof. DO NOT USE WHEN: creating generic entities; use orgx_write.

orgx_act

orgx_plan

Use when planning should survive the session and become executable context instead of a lost chat draft. Starts, resumes, edits, improves, or completes a tracked OrgX planning session. Per-action input requirements: • action="start" → REQUIRES feature_name. Optional: initial_plan (markdown to seed the session). • action="resume" → REQUIRES session_id. • action="improve" → REQUIRES session_id AND plan_content (the current draft to critique). • action="record_edit" → REQUIRES session_id AND edit_summary (one-line description of the change). • action="complete" → REQUIRES session_id AND plan_content (the final accepted plan). Optional: attach_to (target entity to link the completed plan to). USE WHEN: work is still in planning or should become executable context. NEXT: use orgx_write or orgx_act after the plan is accepted and needs durable execution state. DO NOT USE WHEN: directly scaffolding a full initiative hierarchy; use scaffold_initiative for that compatibility path.

orgx_spawn

Use when the user says "delegate this and tell me when it's done," or when you must check whether delegation is allowed before dispatching. Guards, estimates, classifies, spawns, or hands off specialist agent work. Per-action requirements: spawn from an existing task REQUIRES task_id; ad-hoc spawn REQUIRES title + instructions and should include agent_type. handoff REQUIRES task_id + agent_type. guard REQUIRES agent_type. classify REQUIRES title or task_id. action="estimate" REQUIRES title or task_id, returns candidate routes/cost context, and runs without dispatching work. Routing policy: omit model_tier/provider/model for OrgX auto-routing. Set model_tier, provider, model, budget_mode, or max_cost_usd only when the user, policy, or verification plan constrains routing. For controlled reliability validation, use model_tier="standard" and budget_mode="cheapest_valid". USE WHEN: explicitly delegating work to an OrgX agent or checking if delegation is allowed. NEXT: use orgx_inspect or orgx_search to monitor the delegated work, then orgx_submit_receipt for proof. DO NOT USE WHEN: only creating a task row; use orgx_write.

orgx_decide

Use when the user says "remember this decision," asks "what did we decide about X," or agent work needs human approval before it proceeds. Creates, approves, rejects, remembers, or lists durable OrgX decisions. Per-action input requirements: • action="list_pending" → No required fields. Optional: initiative_id, workspace_id (scope filters). • action="create" → REQUIRES title AND decision (the resolved decision text). Recommended: context, initiative_id. • action="remember" → REQUIRES decision (the text to capture as a remembered decision). Optional: title, context. • action="approve" → REQUIRES decision_id. Optional: note (free-text approver rationale). • action="reject" → REQUIRES decision_id AND reason (explanation shown to the assigned agent). USE WHEN: capturing judgment, approval, rejection, or pending decision review. NEXT: use orgx_act, orgx_write, or orgx_spawn only after the decision resolves the next action. DO NOT USE WHEN: writing non-decision entities; use orgx_write.

orgx_submit_receipt

Use when the user says "show me it actually shipped" — completion must be proven with evidence, not prose. Submits a durable receipt anchored to an OrgX entity or artifact. Required: receipt_type + summary. Strongly recommended: one anchor (entity_type+entity_id OR artifact_id), artifact_type, business_outcome, agent_type, and a verifiable URL in evidence. Recognized receipt_type: "proof", "outcome" (measurable result), "quality" (review/score), "attribution" (credit link to revenue/value), "learning" (distilled lesson). Custom keys also accepted. Recognized evidence shapes (mix and match): { prs: string[] } — GitHub PR URLs. { deploys: string[] } — deployment URLs. { test_runs: string[] } — CI run URLs. { metrics: { name, value, unit? }[] } — quantitative outcomes. { links: string[] }, { notes: string } — supporting URLs/text. Pass idempotency_key when retrying — server deduplicates. USE WHEN: closing the loop on agent work with provenance. Receipts should prove the practical artifact and its business outcome, not just say the agent finished. NEXT: orgx_recommend or orgx_search to find the next priority. DO NOT USE for telemetry — use orgx_emit_activity.

recall_memory

Use when the user asks "what did we decide about X" or prior context must be recovered from team memory. Searches organizational memory for prior decisions, artifacts, project context, and team knowledge. Also known as: search memory, recall decisions, find context, retrieve artifacts, what did we decide.

approve_agent_work

Use when agent work is paused waiting for a human yes — review pending decisions, then approve or reject them. Also known as: pending approvals, agent blocked, sign off, review decisions, approve AI work. Per-action input requirements: • action="list" (default when action omitted) → No required fields. Optional filters: limit, urgency_filter, initiative_id. • action="approve" → REQUIRES decision_id. Optional: note (free-text approver rationale). • action="reject" → REQUIRES decision_id AND reason (explanation shown to the assigned agent so it can adjust its next attempt).

delegate_agent_task

Use when the user says "delegate this and tell me when it's done" — assign work to a specialist AI agent that owns the task and reports back with results. Also known as: hand this off, spawn agent, assign task, delegate to agent, have an AI agent do it.

track_project_progress

Use when the user asks how a project is going, what is blocked, or whether an initiative is on track. Returns health, blockers, milestones, owners, and recent activity. Also known as: project status, initiative pulse, blockers, roadmap progress, execution health.

scaffold_initiative

Use when a goal, roadmap, or launch plan exists only as prose and must become owned, executable work. Turns an objective, roadmap, launch, or feature plan into executable workstreams, milestones, and tasks. Also known as: Scaffold an initiative hierarchy, scaffold project, create roadmap, generate execution plan, build a workstream tree. Minimum required input: title. Conditionally required: • workspace_id — REQUIRED unless the MCP session already carries workspace context (resolve via list_entities type=command_center or get_org_snapshot). • objective_ids (or goal_ids) — REQUIRED only when workspace policy enforces a primary objective. objective_ids is the preferred alias; goal_ids carries the same content for API compatibility. Per-nested-entity rules (when workstreams[]/milestones[]/tasks[] are provided): • Each workstream MUST have either "title" or "name" set (they are aliases — provide one). • Each milestone MUST have "title" set. • Each task MUST have "title" set. • All other workstream/milestone/task fields are optional and can be omitted — the scaffold builder auto-fills defaults for missing domain/duration/owner/agent/budget. • "ref" is a client-side label used inside this single call (in depends_on and ref_map). It is not persisted as an ID. Agent-safe aliases that are accepted and normalized server-side: task priority "urgent" → "high"; task/milestone status "active" → "in_progress". Source verification gate: when the initiative is based on a named external product or URL, verify the actual target in a browser or from user-provided screenshots before creating records. Pass source_evidence. If the target cannot be rendered, do not infer the product from web-search results; use mode="draft" with verification_state="unverified" and ask for evidence. USE WHEN: user wants to plan a new initiative from scratch. NEXT: use mode="launch" to create and start agents (default), mode="scaffold" to create without launching, or mode="draft" to validate the plan without writes. The result returns initiative_id, ref_map, and preferred_next_calls for orgx_inspect/orgx_search/orgx_write chaining. DO NOT USE: for adding a single task to an existing initiative — use create_entity instead.

review_artifact

Use when the user asks to review work, sign off on a deliverable, or clear pending artifact reviews. Surfaces the next artifact awaiting review and renders the artifact-review widget with a preview, version filmstrip, and hold-to-approve / request-changes actions. USE WHEN the user asks to review work, approve a deliverable, or handle pending artifact reviews. DO NOT USE for listing all artifacts — use list_entities type=artifact instead.

get_morning_brief

Use when the user asks 'what happened,' 'catch me up,' or starts a session after time away. Returns curated receipts, exceptions, ROI delta, and value signals from the most recent autonomous session. The brief IS curated receipts, not a separate data structure. Prefer `get_morning_brief` with workspace brief with value and exception summaries for new prompts, skills, and examples.