OrgX
useorgx/orgx-mcpOrgX 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, design) and monitor their progress Query organizational memory — search past decisions, artifacts, and learnings across initiatives Track progress — get initiative health, agent status, blockers, and morning briefs Plan and prioritize — score queues, get next-action recommendations, and run autonomous sessions with budget guardrails OrgX is built for solo founders and small teams who work across multiple AI tools and lose context between sessions. Instead of manually shuttling context between Claude, Cursor, and ChatGPT, OrgX holds the organizational graph so every tool sees the same state.
Score: 100/100
Handshake verified by our own probe.
why this score
Tools · 41
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. U…
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 …
Use when the user asks what agents are working on right now, whether delegated work is still running, or why nothing has landed yet. Successful calls record metered MCP allowance usage but do not chan…
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, retrie…
Use when the user asks how a project is going, what is blocked, or whether an initiative is on track. Successful calls record metered MCP allowance usage but do not change business records. Also known…
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, sp…
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 …
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 ru…
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, res…
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/we…
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 exis…
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…
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…
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 anot…
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…
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 ru…
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…
Emit the deterministic execution graph + trust ledger for the active run from explicit nodes, OTel semantic events, or both. OTel promotion requires orgx.material=true plus episode/kind attributes; in…
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 receip…
Queue OrgX's independent evaluator for one completed agent artifact. The producing agent cannot supply or choose the score. OrgX persists the native evaluation and its 1–5 rating projection under the …
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, returns the v2 tool routing ma…
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 ent…
Read the exact workspace-scoped projection for one domain controller without reconciling or triggering a run. USE WHEN: verifying whether a controller ran, its latest outcome, signal, receipt, project…
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, memory, and the work ledg…
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 prioritizat…
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…
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 contex…
Act on one OrgX entity. Required inputs: • update → "fields" patch object. • complete_with_proof, ship_batch → "artifact" (artifact_type + artifact_url/external_url; preview_markdown optional). …
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 inp…
Delegate specialist work or check whether delegation is allowed. Actions: guard, estimate, classify, spawn, and handoff. Requirements: existing-task spawn needs task_id; ad-hoc spawn needs title + in…
Creates or remembers durable OrgX decisions, lists pending decisions, and opens human review. Approval and rejection are human-session-only: those actions return a review URL and never resolve the dec…
Pre-registers one delayed, workspace-level outcome against an exact observer before its measurement window starts. The current bounded contract supports only orgx.run_receipt_coverage.v1: the share of…
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 + s…
Use during a long-running session to read accepted material state changes since orgx_bootstrap. Pass the exact capsule_id and as_of_global_sequence returned by bootstrap. Returns only the currently le…
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 knowle…
Use when agent work is paused waiting for a human yes — list pending decisions and open the human review surface. Listing may record usage or session state, so this tool is not read-only. Approval and…
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, as…
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, …
Turn a goal, roadmap, launch, or feature plan into one owned initiative with workstreams, milestones, and tasks. Minimum input is title; workspace context is resolved from the session when omitted. wo…
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, v…
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. …
Resources · 28
Pending Decisions Widget
ui://widget/decisions.html?v=7d00aaa4ace1
Pending Decisions Widget (ChatGPT)
ui://widget/decisions.skybridge.html?v=7d00aaa4ace1
Agent Status Widget
ui://widget/agent-status.html?v=7d00aaa4ace1
Agent Status Widget (ChatGPT)
ui://widget/agent-status.skybridge.html?v=7d00aaa4ace1
Search Results Widget
ui://widget/search-results.html?v=7d00aaa4ace1
Search Results Widget (ChatGPT)
ui://widget/search-results.skybridge.html?v=7d00aaa4ace1
Scaffolded Initiative Widget
ui://widget/scaffolded-initiative.html?v=7d00aaa4ace1
Scaffolded Initiative Widget (ChatGPT)
ui://widget/scaffolded-initiative.skybridge.html?v=7d00aaa4ace1
Initiative Pulse Widget
ui://widget/initiative-pulse.html?v=7d00aaa4ace1
Initiative Pulse Widget (ChatGPT)
ui://widget/initiative-pulse.skybridge.html?v=7d00aaa4ace1
Task Spawned Widget
ui://widget/task-spawned.html?v=7d00aaa4ace1
Task Spawned Widget (ChatGPT)
ui://widget/task-spawned.skybridge.html?v=7d00aaa4ace1
Workspace Map Widget
ui://widget/workspace-map.html?v=7d00aaa4ace1
Workspace Map Widget (ChatGPT)
ui://widget/workspace-map.skybridge.html?v=7d00aaa4ace1
Entity Card Widget
ui://widget/entity-card.html?v=7d00aaa4ace1
Entity Card Widget (ChatGPT)
ui://widget/entity-card.skybridge.html?v=7d00aaa4ace1
Work Ledger Widget
ui://widget/work-ledger.html?v=7d00aaa4ace1
Work Ledger Widget (ChatGPT)
ui://widget/work-ledger.skybridge.html?v=7d00aaa4ace1
Morning Brief Widget
ui://widget/morning-brief.html?v=7d00aaa4ace1
Morning Brief Widget (ChatGPT)
ui://widget/morning-brief.skybridge.html?v=7d00aaa4ace1
Artifact Review Widget
ui://widget/artifact-review.html?v=7d00aaa4ace1
Artifact Review Widget (ChatGPT)
ui://widget/artifact-review.skybridge.html?v=7d00aaa4ace1
Plan Session Live Widget
ui://widget/plan-session-live.html?v=7d00aaa4ace1
Plan Session Live Widget (ChatGPT)
ui://widget/plan-session-live.skybridge.html?v=7d00aaa4ace1
List of downloadable OrgX skill packs
orgx://skills/catalog
Morning Briefing skill pack
orgx://skills/morning-briefing
Initiative Kickoff skill pack
orgx://skills/initiative-kickoff
Bulk Create skill pack
orgx://skills/bulk-create
Prompts · 5
Create an initiative plus supporting milestones and tasks
Plan a feature with automatic improvement suggestions and pattern learning. Use this when the user wants to plan a new feature.
Discover your learned planning patterns and skills
E2E run: agent loop + MCP Apps widgets + context survival (real data)
Alias for thursday-e2e
Similar MCP servers embedding-nearest
How to use
Add to your Claude Desktop / Cursor / Cline MCP config:
{
"mcpServers": {
"orgx": {
"url": "https://mcp.useorgx.com",
"transport": "http"
}
}
}