OrgX MCP — Organizational Continuity for AI Agents

useorgx/orgx-mcp

This one gives Claude, Cursor, and ChatGPT shared access to organizational memory and decision workflows. You get tools to approve or reject decisions with notes, spawn agent tasks, track initiative health, and search semantically across all captured artifacts. It auto-tags work by domain (Product, Engineering, Marketing, Sales) so context from a spec you wrote in Claude shows up when someone drafts the launch email in ChatGPT. The API includes get_pending_decisions, spawn_agent_task, orgx_search, and planning session tools. Connects via streamable HTTP or SSE. Reach for it when you want async work across tools to build on itself instead of starting from zero every time.

GitHub stars: 2
tools: 28
transport: HTTP, SSE
last updated: Oct 15, 2026

View on GitHub

Tools

28 tools

Public tool metadata for what this MCP can expose to an agent.

approve_decisionApprove a pending agent decision after explicit user confirmation. 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_d...4 params

Approve a pending agent decision after explicit user confirmation. 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_d...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

decision_idstring

Decision ID to approve

notestring

Optional note recorded with the approval

option_idstring

Optional decision option id when the decision includes selectable options.

reject_decisionReject a pending agent decision with guidance after explicit user confirmation. 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...4 params

Reject a pending agent decision with guidance after explicit user confirmation. 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...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

decision_idstring

Decision ID to reject

option_idstring

Optional decision option id when the decision includes selectable options.

reasonstring

Reason for rejecting the decision

get_agent_statusShow current AI agent activity, blocked work, and execution state. 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_...3 params

Show current AI agent activity, blocked work, and execution state. 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_...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

agent_idstring

Optional agent ID to inspect

include_idleboolean

Include idle agents in the response

query_org_memorySearch team memory, organizational decisions, prior artifacts, and project context across agents. 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 re...4 params

Search team memory, organizational decisions, prior artifacts, and project context across agents. 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 re...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

limitnumber

Maximum number of results to return

querystring

Search query for OrgX memory

scopestring

Optional scope filter for the memory searchone of all · artifacts · decisions · initiatives

get_initiative_pulseGet project health, blockers, milestones, owners, and recent activity for an initiative. 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 enti...3 params

Get project health, blockers, milestones, owners, and recent activity for an initiative. 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 enti...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

initiative_idstring

Optional: Initiative UUID to check.

initiative_namestring

Optional: Initiative title to resolve automatically if ID is unknown.

spawn_agent_taskDelegate work to a specialist AI agent and track the assigned task. 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. O...17 params

Delegate work to a specialist AI agent and track the assigned task. 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. O...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

agentstring

Target agent identifier or alias

budget_modestring

Optional budget posture override. Omit to let OrgX apply workspace policy. Use cheapest_valid for controlled reliability/validation runs where cost must be pinned while the loop is being proven.one of cheapest_valid · balanced · highest_quality

contextstring

Optional supporting context or background for the task

deadlinestring

Optional: When this is needed by (ISO date or plain text).

execution_targetstring

Where to execute: cloud (default), local (on your machine), local_preferred (try local first), or auto.one of auto · cloud · local · local_preferred

expected_artifactsarray

Optional: Final outputs you expect (e.g., "PRD", "10 ad images").

initiative_idstring

Optional initiative UUID to associate with the spawned task

initiative_namestring

Optional: Initiative title to resolve automatically if ID is unknown.

max_cost_usdnumber

Optional per-task hard cost ceiling in USD. If the estimate exceeds this, OrgX should block, downgrade, or ask for approval before dispatch.

modelstring

Optional exact model identifier when the user explicitly chooses one. Omit to let OrgX resolve the model from task, tier, provider, policy, and budget.

model_tierstring

Optional model tier override. Omit to let OrgX auto-route according to task complexity. Use standard for controlled verification runs; use balanced or precision when explicitly selected by the user...one of standard · balanced · precision · local · sonnet · opus

providerstring

Optional provider preference. Use auto unless the user requests a specific provider or the budget/capability comparison has selected one.one of auto · openai · anthropic · openrouter · groq · local

sdk_backendstring

Preferred execution backend. Use openai for cloud-safe execution, claude for Claude SDK routing, or auto to let OrgX decide.one of auto · openai · claude

style_guidelinesstring

Optional: Voice/format/style constraints for the agent.

taskstring

Task instructions for the target agent

wait_for_completionboolean

Optional: If true and safe, wait briefly for the first result before replying.

handoff_taskReassign work to another specialist AI agent and optionally spawn a new run. 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...5 params

Reassign work to another specialist AI agent and optionally spawn a new run. 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...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

agentstring

Target agent (e.g., "engineering-agent", "marketing-agent")

notestring

Handoff note: what to do, constraints, context, definition of done

spawnboolean

If true (default), spawn a new agent run for the target agent

task_idstring

Task UUID to hand off

recommend_next_actionRecommend what should happen next based on progress gaps, blockers, and execution templates. Also known as: next best action, prioritize work, unblock project. USE WHEN: user asks what to do next, or needs help prioritizing. NEXT: Execute the recommended action (entity_action,...7 params

Recommend what should happen next based on progress gaps, blockers, and execution templates. Also known as: next best action, prioritize work, unblock project. USE WHEN: user asks what to do next, or needs help prioritizing. NEXT: Execute the recommended action (entity_action,...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

cascadeboolean

If true, refresh recommendations across the entity chain first

command_center_idstring

Deprecated alias for workspace_id.

entity_idstring

Entity ID. For workspace, use "default" or a workspace ID.

entity_typestring

Entity type to recommend for (default: workspace)one of workspace · initiative · workstream · milestone

limitnumber

Max recommendations to return (default 5, max 5)

workspace_idstring

Optional workspace ID to scope recommendations (canonical).

orgx_emit_activityEmit 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" record...13 params

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" record...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

chokepointobject

Durable blocker/stall/error/approval to surface in /live when execution cannot proceed

correlation_idstring

Required when run_id is not provided

initiative_idstring

Initiative UUID

levelstring

Optional severity level for the activity eventone of info · warn · error

messagestring

Human-readable activity update

metadataobject

Optional structured metadata to attach to the activity event

next_stepstring

Optional next step to surface after this activity event

phasestring

Optional reporting phase for the activity eventone of intent · execution · blocked · review · handoff · completed

progress_pctnumber

Optional progress percentage associated with this activity

run_idstring

Existing run UUID

runtimeobject

Runtime provenance used by /live to bucket cloud, local, Anthropic, managed, and OpenClaw chokepoints

source_clientstring

Required when run_id is not providedone of openclaw · codex · claude-code · chatgpt · cursor · web-ui

consolidate_prGenerate 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 ano...9 params

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 ano...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

commit_shastring

Override commit SHA for idempotency; defaults to merge commit or PR head SHA

decision_idstring

Decision to attach the consolidation_pass artifact to

initiative_idstring

Initiative to attach the consolidation_pass artifact to

pr_urlstring

GitHub pull request URL, e.g. https://github.com/org/repo/pull/123. OrgX must have server-side GitHub credentials to inspect it.

reviewer_notestring

Optional reviewer note to include in critic evidence

task_idstring

Task to attach the consolidation_pass artifact to

verdictstring

Optional verdict override; defaults from PR stateone of ship · simplify_first · escalate

workspace_idstring

OrgX workspace UUID

orgx_bootstrapEstablish OrgX session context, discover granted scopes, and get 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...5 params

Establish OrgX session context, discover granted scopes, and get 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...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

client_namestring

Optional MCP client name, such as codex, chatgpt, cursor, or claude

conversation_idstring

Optional client conversation/session identifier for continuity

timezonestring

Optional user timezone for date-sensitive readouts

workspace_idstring

Canonical workspace UUID to bind as the active session workspace

orgx_inspectHydrate one OrgX entity with execution context. USE WHEN: the user names a specific task, milestone, initiative, decision, artifact, or plan session and needs details before acting. NEXT: use orgx_act, orgx_attach, or orgx_write if the user asks to change what you inspected. D...6 params

Hydrate one OrgX entity with execution context. USE WHEN: the user names a specific task, milestone, initiative, decision, artifact, or plan session and needs details before acting. NEXT: use orgx_act, orgx_attach, or orgx_write if the user asks to change what you inspected. D...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

hydrate_contextboolean

Include linked context where available; default true

idstring

Entity UUID or accepted short ID prefix

max_charsinteger

Approximate maximum hydrated context characters

session_idstring

Optional bootstrap/session identifier

typestring

Entity type to inspectone of initiative · workstream · milestone · task · decision · artifact

orgx_searchFind OrgX entities, decisions, artifacts, and memory. USE WHEN: browsing work, searching memory, finding IDs, or listing related records. NEXT: use 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...9 params

Find OrgX entities, decisions, artifacts, and memory. USE WHEN: browsing work, searching memory, finding IDs, or listing related records. NEXT: use 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...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

fieldsarray

Optional compact field list

initiative_idstring

Optional initiative UUID scope

limitinteger

Maximum records to return

querystring

Search query for memory or title/text matching

session_idstring

Optional bootstrap/session identifier

statusstring

Optional status filter

typestring

Optional entity type filter, such as task, milestone, decision, artifact, or initiative

workspace_idstring

Optional workspace UUID scope

orgx_recommendRecommend next work, summarize morning-brief signals, or read prioritization context. USE WHEN: user asks what to do next, wants a brief, or needs priority guidance. NEXT: present the recommendation, then use orgx_act, orgx_write, or orgx_spawn only after the user confirms an...7 params

Recommend next work, summarize morning-brief signals, or read prioritization context. USE WHEN: user asks what to do next, wants a brief, or needs priority guidance. NEXT: present the recommendation, then use orgx_act, orgx_write, or orgx_spawn only after the user confirms an...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

entity_idstring

Scoped entity ID

entity_typestring

Recommendation scope typeone of workspace · initiative · workstream · milestone · task

limitinteger

Maximum recommendations

modestring

Recommendation mode; default next_actionone of next_action · morning_brief

session_idstring

Optional bootstrap/session identifier

workspace_idstring

Workspace UUID

orgx_writeCreate or update one OrgX record (snake_case fields). Operations: create (default) uses per-type fields; update REQUIRES id + fields. Create requirements: initiative title/name + workspace_id + goal_ids when the workspace enforces primary objectives; workstream title + initiat...34 params

Create or update one OrgX record (snake_case fields). Operations: create (default) uses per-type fields; update REQUIRES id + fields. Create requirements: initiative title/name + workspace_id + goal_ids when the workspace enforces primary objectives; workstream title + initiat...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

artifact_typestring

REQUIRED when type="artifact". Artifact type code. Preferred founder/team examples: orchestration.next_initiative, eng.pull_request, eng.deploy_proof, eng.structured_blocker, sales.strategy, sales....

artifact_urlstring

Internal artifact URL (e.g. /api/artifacts/...). Either artifact_url or external_url is required when type="artifact"; preview_markdown alone is not accepted.

blocker_typestring

Blocker category/type when type="blocker" (e.g. "missing_input", "permission", "external_dependency").

descriptionstring

Longer-form description used in detail views.

due_datestring

Due date as YYYY-MM-DD for supported entity types. Do not send due_date when type="initiative"; put initiative target dates in metadata.

entity_idstring

REQUIRED when type="artifact" (unless task_id is provided). UUID of the entity to attach the artifact to.

entity_typestring

REQUIRED when type="artifact". Entity type to attach the artifact to (initiative, workstream, milestone, task, or decision).

external_urlstring

External artifact URL (https://). Either artifact_url or external_url is required when type="artifact"; preview_markdown alone is not accepted.

fieldsobject

REQUIRED when operation="update". Map of entity fields to patch (only include fields you want to change).

goal_idsarray

Objective UUIDs for initiative/workstream/milestone/task creation. REQUIRED when the workspace enforces a primary objective. Resolve via orgx_inspect type=objective.

idstring

REQUIRED when operation="update". Target entity UUID to patch.

idempotency_keystring

Strongly recommended client-generated idempotency key for safe retries. Same key returns the same result without creating a duplicate.

initiative_idstring

Parent initiative UUID. REQUIRED when type="workstream". Optional context for tasks/milestones/artifacts to associate them with an initiative.

live_publicboolean

Shortcut to publish an initiative live link (sets live_visibility="public"). Only applies when type="initiative".

live_reveal_titleboolean

When true, public live-link visitors see the initiative title. Only applies when type="initiative" with live_visibility="public".

live_visibilitystring

Initiative live-link visibility. Only applies when type="initiative".one of private · public

metadataobject

Free-form object for type-specific metadata. Schema varies per entity type (e.g. for skills: { capabilities, guardrails, channels }; for studio_brand: { tokens, voice, exemplars }).

milestone_idstring

Parent milestone UUID for tasks. Some workspaces require an explicit backlog milestone under the workstream; create/resolve that milestone first instead of relying on auto-resolution.

namestring

Alternative to "title" on create. REQUIRED on create when "title" is not provided.

+14 more parameters. See the server's own documentation for the full schema.

orgx_attachAttach a durable artifact or proof URL to an existing 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 practica...19 params

Attach a durable artifact or proof URL to an existing 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 practica...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

agent_typestring

Agent/domain that produced the artifact, such as engineering, sales, product, design, operations, marketing, or orchestrator. Stored under metadata.artifact_contract.

artifact_typestring

Artifact type code. Preferred founder/team examples: orchestration.next_initiative, eng.pull_request, eng.deploy_proof, eng.structured_blocker, sales.strategy, sales.icp_offer_sequence, sales.send_...

artifact_urlstring

Internal artifact URL. REQUIRED unless external_url is provided; preview_markdown alone is rejected.

business_outcomestring

Business outcome this artifact is meant to advance, such as ship a PR, start founder-led sales, unblock launch, reduce incident risk, or choose the next initiative. Stored under metadata.artifact_c...

company_stagestring

Founder/team context this artifact is calibrated for. Stored under metadata.artifact_contract.one of early_founder · founder_led_company · operating_team

descriptionstring

Artifact description

external_urlstring

External artifact URL. REQUIRED unless artifact_url is provided; preview_markdown alone is rejected.

idstring

Target entity UUID or short ID prefix

idempotency_keystring

Strongly recommended client-generated idempotency key for safe retries

metadataobject

Artifact metadata

namestring

Artifact title

ownerstring

Human or agent owner for the next review/action. Stored under metadata.artifact_contract.

preview_markdownstring

Optional markdown preview shown with the linked artifact. Does not replace artifact_url/external_url.

review_datestring

Date or cadence for the next review point. Stored under metadata.artifact_contract.

session_idstring

Optional bootstrap/session identifier

statusstring

Artifact workflow statusone of draft · in_review · approved · changes_requested · superseded · archived

typestring

Target entity typeone of initiative · milestone · workstream · task · objective · playbook

verificationarray

Verification evidence or checks required before the artifact can count as done. Stored under metadata.artifact_contract.

orgx_actRun a lifecycle, validation, completion, or proof action on one OrgX entity. Per-action required inputs: • update → "fields" patch object. • complete_with_proof, ship_batch → "artifact" (artifact_type + artifact_url/external_url; preview_markdown optional). • validate (studio)...14 params

Run a lifecycle, validation, completion, or proof action on one OrgX entity. Per-action required inputs: • update → "fields" patch object. • complete_with_proof, ship_batch → "artifact" (artifact_type + artifact_url/external_url; preview_markdown optional). • validate (studio)...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

actionstring

Lifecycle action to execute on the target entity. Must be valid for the given type — see tool description for the (type → action) matrix.one of launch · pause · resume · complete · complete_with_proof · archive

artifactobject

REQUIRED when action=complete_with_proof or action=ship_batch. Proof artifact payload. Expected shape: { artifact_type: string, artifact_url?: string, external_url?: string, preview_markdown?: stri...

dry_runboolean

Preview update/delete or supported lifecycle actions without mutating. For action=update this returns would_update and must not delegate to orgx_write.

fieldsobject

REQUIRED when action=update. Map of entity fields to patch (e.g. { name?: string, description?: string, owner_id?: string, status?: string, due_date?: string }). Only include fields you want to cha...

forceboolean

Force action where server supports override semantics (skips pre-flight checks).

idstring

Target entity UUID or short ID prefix (8+ hex chars).

idempotency_keystring

Optional client-supplied idempotency key for safe retries. Same key returns the same result without re-executing.

notestring

Strongly recommended for destructive or blocking actions (block, flag_risk, decline, supersede, cancel, delete). Free-text rationale shown in audit history and downstream agent context.

quality_scorenumber

Quality score (0-5) attached to the action when used in proof/completion flows.

session_idstring

Optional bootstrap/session identifier returned by orgx_bootstrap.

specobject

REQUIRED when action=validate. Spec payload for studio validation (shape varies per studio entity subtype).

typestring

Target entity type (initiative, milestone, workstream, task, objective, playbook, decision, or studio).one of initiative · milestone · workstream · task · objective · playbook

verificationarray

Optional list of verification evidence URLs/IDs for completion flows.

orgx_planStart, resume, edit, improve, or complete 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 ses...10 params

Start, resume, edit, improve, or complete 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 ses...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

actionstring

Planning action to perform. See top-level description for per-action required fields.one of start · resume · improve · record_edit · complete

attach_toobject

Optional target to link the completed plan to when action=complete. Shape: { entity_type: "initiative" | "workstream" | "task", entity_id: string }.

edit_summarystring

One-line description of the change being recorded. REQUIRED when action=record_edit.

feature_namestring

Feature or plan name. REQUIRED when action=start.

idempotency_keystring

Optional idempotency key for safe retries. Same key returns the same result without creating duplicate session state.

initial_planstring

Markdown plan content to seed the new session. Optional on action=start; the session can also be started empty and filled via improve/record_edit.

plan_contentstring

Current/final plan markdown. REQUIRED when action=improve (the draft to critique) or action=complete (the final accepted plan).

session_idstring

Plan session UUID or orgx://plan_session/<uuid> URI. REQUIRED for action=resume | improve | record_edit | complete. Omit for action=start.

workspace_idstring

Workspace UUID to scope action=start plan sessions. Defaults to current session workspace when omitted.

orgx_spawnGuard, estimate, classify, spawn, or hand 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_typ...15 params

Guard, estimate, classify, spawn, or hand 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_typ...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

actionstring

Spawn operation. Defaults to "spawn". Use estimate for pre-spawn cost/routing context without dispatching work. See top-level description for per-action required fields.one of guard · estimate · spawn · handoff · classify

agent_typestring

Target agent type/domain (e.g. "engineering", "marketing", "design"). REQUIRED for action=guard or action=handoff. Strongly recommended for action=spawn so the work routes to the right specialist.

budget_modestring

Optional budget posture override. Use cheapest_valid for controlled validation runs while reliability is being proven.one of cheapest_valid · balanced · highest_quality

idempotency_keystring

Optional client-supplied idempotency key for safe retries. Same key returns the same spawn result without re-running.

initiative_idstring

Optional initiative UUID to scope the spawned task. Inferred from task_id when omitted.

instructionsstring

Delegation instructions for the agent. REQUIRED for action=spawn when spawning ad-hoc (without task_id). Used to override the task description for action=handoff.

max_cost_usdnumber

Optional per-task hard cost ceiling in USD. If the estimate exceeds this, OrgX should block, downgrade, or request approval before dispatch.

modelstring

Optional exact model identifier when the user explicitly selects one. Otherwise OrgX resolves the model from task, tier, provider, policy, and budget.

model_tierstring

Optional model tier override. Omit to let OrgX auto-route from task complexity. Legacy local/sonnet/opus are accepted for older clients.one of standard · balanced · precision · local · sonnet · opus

providerstring

Optional provider preference. Use auto unless the user asks for a specific provider or a cost comparison selects one.one of auto · openai · anthropic · openrouter · groq · local

session_idstring

Optional bootstrap/session identifier returned by orgx_bootstrap.

task_idstring

Existing task UUID. REQUIRED for action=handoff. REQUIRED for action=spawn when spawning work for an already-created task. Either task_id or title (with instructions) must be provided for action=sp...

titlestring

Task title. REQUIRED for ad-hoc spawn (action=spawn without task_id) or action=classify without task_id. Used as the human-readable label of the spawned task.

workspace_idstring

Optional workspace UUID to scope the spawned task. Defaults to the MCP session's workspace.

orgx_decideCreate, approve, reject, remember, or list 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)....13 params

Create, approve, reject, remember, or list 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)....

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

actionstring

Decision operation. See top-level description for per-action required fields.one of create · remember · list_pending · approve · reject

contextstring

Background context / rationale that led to the decision. Recommended for action=create to capture provenance.

decisionstring

The decision text itself (what was decided). REQUIRED for action=create and action=remember.

decision_idstring

Decision UUID. REQUIRED for action=approve or action=reject. Returned by action=list_pending or action=create.

idempotency_keystring

Strongly recommended client-supplied idempotency key for writes (action=create, remember, approve, reject). Same key returns the same result without duplicating state.

initiative_idstring

Optional initiative UUID to scope the decision. Used as filter when action=list_pending; used as parent when action=create.

notestring

Optional approver note for action=approve. Free-text rationale stored in audit history.

reasonstring

REQUIRED for action=reject. Explanation of why the decision was rejected — used by the assigned agent to adjust its next attempt.

session_idstring

Optional bootstrap/session identifier returned by orgx_bootstrap.

summarystring

Optional one-line summary used in lists. Falls back to title when omitted.

titlestring

Short title for the decision. REQUIRED for action=create.

workspace_idstring

Optional workspace UUID to scope the decision. Defaults to the MCP session's workspace.

orgx_submit_receiptSubmit a durable receipt (proof, outcome, quality, attribution, or learning) 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 at l...19 params

Submit a durable receipt (proof, outcome, quality, attribution, or learning) 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 at l...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

agent_typestring

Agent/domain that produced the receipt, such as engineering, sales, product, design, operations, marketing, or orchestrator.

artifact_idstring

Related artifact UUID to anchor the receipt to. Alternative to entity_type+entity_id when the proof lives in OrgX as an artifact.

artifact_typestring

Artifact type this receipt proves. Preferred founder/team examples: orchestration.next_initiative, eng.pull_request, eng.deploy_proof, eng.structured_blocker, sales.strategy, sales.icp_offer_sequen...

budget_modestring

Budget posture used for the run being receipted. For validation rungs before calibrated expansion, use cheapest_valid.one of cheapest_valid · balanced · highest_quality

business_outcomestring

Business outcome advanced by the receipt.

entity_idstring

Related entity UUID. Required when entity_type is provided.

entity_typestring

Related entity type (initiative, workstream, milestone, task, decision). Required if no artifact_id is provided — pair with entity_id.

evidenceobject

Structured evidence payload. Recognized shapes: { prs: string[] }, { deploys: string[] }, { test_runs: string[] }, { metrics: { name, value, unit? }[] }, { links: string[] }, { notes: string }. See...

idempotency_keystring

Strongly recommended client-supplied idempotency key. Submitting the same key twice will not create a duplicate receipt.

loop_validationboolean

Set true when this receipt should be evaluated against the OrgX loop reliability validation ladder.

max_cost_usdnumber

Per-task or canary spend cap used during the validation run, when known.

model_tierstring

Model tier used for the run being receipted. For validation rungs before calibrated expansion, use standard.one of standard · balanced · precision · local · sonnet · opus

receipt_typestring

Receipt category key. Recognized values: "proof", "outcome", "quality", "attribution", "learning". Custom domain-specific keys are also accepted.

session_idstring

Optional bootstrap/session identifier returned by orgx_bootstrap.

summarystring

One-sentence human-readable description of what the receipt proves (e.g. "Merged PR #142 unblocking the auth refactor").

validation_rungstring

Optional OrgX loop validation rung this receipt proves. Required for promotion-grade loop validation receipts.one of

schema_discovery · dry_run_spawn · single_domain_fixture · cross_domain_initiative_fixture · overnight_canary · calibrated_auto_route_expansion

verification_statusstring

Whether the artifact verification passed, failed, was blocked, or was not run.one of passed · failed · blocked · not_run

workspace_idstring

Workspace UUID. Defaults to the MCP session's workspace when omitted.

recall_memorySearch 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.4 params

Search 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.

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

limitnumber

Maximum number of results to return

querystring

Search query for organizational memory

scopestring

Optional scope filter for the memory searchone of all · artifacts · decisions · initiatives

approve_agent_workReview or act on agent decisions awaiting human approval. 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, u...8 params

Review or act on agent decisions awaiting human approval. 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, u...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

actionstring

Operation to perform. Defaults to "list" (returns pending approvals). Use "approve" or "reject" to act on a specific decision_id.one of list · approve · reject

decision_idstring

REQUIRED when action="approve" or action="reject". Decision UUID from the pending approvals list.

initiative_idstring

Used only when action="list". Scopes pending decisions to a specific initiative UUID.

limitnumber

Used only when action="list" (or omitted). Max pending decisions to return.

notestring

Optional approver note for action="approve". Free-text rationale stored in audit history.

reasonstring

REQUIRED for action="reject". Explanation of why the decision was rejected — used by the agent to adjust its next attempt.

urgency_filterstring

Used only when action="list". Filters the returned pending decisions by urgency.one of all · critical · high

delegate_agent_taskAssign work to a specialist AI agent and track the result. Also known as: hand this off, spawn agent, assign task, delegate to agent, have an AI agent do it.9 params

Assign work to a specialist AI agent and track the result. Also known as: hand this off, spawn agent, assign task, delegate to agent, have an AI agent do it.

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

agentstring

Target agent identifier or alias

contextstring

Optional supporting context or background for the task

deadlinestring

Optional due date or plain-text deadline

expected_artifactsarray

Optional final outputs you expect

initiative_idstring

Optional initiative UUID to associate with the spawned task

initiative_namestring

Optional initiative title to resolve automatically if ID is unknown

style_guidelinesstring

Optional voice, format, or style constraints

taskstring

Task instructions for the target agent

track_project_progressGet health, blockers, milestones, owners, and recent activity for a project or initiative. Also known as: project status, initiative pulse, blockers, roadmap progress, execution health.3 params

Get health, blockers, milestones, owners, and recent activity for a project or initiative. Also known as: project status, initiative pulse, blockers, roadmap progress, execution health.

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

initiative_idstring

Optional initiative UUID to check

initiative_namestring

Optional initiative title to resolve automatically if ID is unknown

scaffold_initiativeTurn an objective, roadmap, launch, or feature plan into executable workstreams, milestones, and tasks. Also known as: scaffold project, create roadmap, generate execution plan. Minimum required input: title. Conditionally required: • workspace_id — REQUIRED unless the MCP ses...20 params

Turn an objective, roadmap, launch, or feature plan into executable workstreams, milestones, and tasks. Also known as: scaffold project, create roadmap, generate execution plan. Minimum required input: title. Conditionally required: • workspace_id — REQUIRED unless the MCP ses...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

command_center_idstring

Deprecated alias for workspace_id to scope the initiative hierarchy

concurrencynumber

Parallel creation concurrency (default 8)

contextarray

Optional context attachments (pointers, not payloads).

continue_on_errorboolean

Continue creating remaining entities after an error

coordination_dependencyobject

The single most important cross-workstream coordination dependency you identified while planning this initiative. Name it specifically based on what the workstreams actually do — not a generic labe...

descriptionstring

Initiative description

external_syncobject

Optional async mirror request for external work trackers. Omit for fastest scaffold response.

goal_idsarray

Optional objective UUIDs for the initiative. OrgX stores workspace objectives in goal_ids; provide at least one to avoid objective-invariant failures.

idempotency_keystring

Optional stable retry key. When omitted, OrgX derives one from workspace, owner, title, objectives, and hierarchy.

launch_after_createboolean

Legacy alias for mode. false maps to mode=scaffold; true maps to mode=launch when mode is omitted.

modestring

Optional stage. draft validates without writes; scaffold creates records without launching agents; launch creates records and starts agents. Defaults to launch for backwards compatibility.one of draft · scaffold · launch

objective_idsarray

Preferred objective UUIDs for the initiative. Normalized to goal_ids for API compatibility.

owner_idstring

Optional owner user ID for the scaffolded initiative; defaults to the authenticated user when omitted

response_modestring

Optional response timing. fast_ack returns after durable record creation and queues launch follow-ups asynchronously; complete waits for agent assignment, launch, and stream snapshot before returni...one of fast_ack · complete

summarystring

Initiative summary

titlestring

Initiative title

user_idstring

Deprecated alias for owner_id; prefer owner_id for new calls

workspace_idstring

Workspace/command center UUID to scope the initiative hierarchy. Required unless the MCP session already has workspace context; resolve with list_entities type=command_center or get_org_snapshot.

workstreamsarray

Nested workstreams. Include domain, dependencies, and estimate fields when possible. If omitted, the scaffold builder auto-fills subtasks/dependencies and OrgX re-estimates domain+agent+cost with m...

review_artifactSurface the next artifact awaiting review. 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 list...4 params

Surface the next artifact awaiting review. 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 list...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

artifact_idstring

Specific artifact ID to review. Defaults to the next in_review artifact.

entity_idstring

Scope to artifacts attached to this entity (initiative, workstream, milestone, or task).

workspace_idstring

Workspace UUID. Defaults to the session workspace.

get_morning_briefCurated 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 exa...3 params

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 exa...

Parameters* required

_contextobject

Client context for conversation tracking (strongly recommended for cross-client continuity)

session_idstring

Specific autonomous session ID; defaults to the most recent session

workspace_idstring

Workspace UUID to load the morning brief for

Readme

OrgX MCP — shared work context for AI agents

For people whose work spans chats, coding clients, and teammates, OrgX MCP connects an AI client to the same workspace record of decisions, tasks, artifacts, approvals, and evidence. A new session can retrieve why a decision was made and what was actually delivered.

UI preview

OrgX MCP widget gallery showing the agent-status widget with synthetic Product and Engineering work, tasks, progress, artifacts and blockers

This current local capture uses the shipped gallery fixtures, with external requests blocked (capture details). Try the live widget gallery to explore example states. In MCP Apps-compatible hosts, widgets render beside tool results; other clients can use the text/structured results. GitHub displays the screenshot, not a running widget.

Quickstart

In an MCP client supporting remote HTTP and OAuth, add:

https://mcp.useorgx.com/mcp

View the full README on GitHub

Details

Repository: github.com/useorgx/orgx-mcp
Website: useorgx.com
Category: Automation & Workflows
Transport: HTTP, SSE
Registry: MCP registry, active

Related Automation & Workflows MCP servers

View all

Pusher Channelscrashbytes/pusher-mcp-serverTrigger events, query channels, and manage realtime messaging on Pusher Channels.2stars

Anime Mcp Servercyanheads/anime-mcp-serverSearch anime/manga, franchise relations, schedule, characters, rankings, studio filmography.2stars

VibeSEOsultanlive/vibeseo-mcpSEO research, keyword discovery, site audits, Search Console, backlinks and content workflow.2stars

Safari DevTools MCPhayodev/safari-devtools-mcpMCP server for Safari DevTools — browser debugging and automation for AI coding agents2stars

ComfyUI Buildermit9/mcp-comfy-ui-builderComfyUI MCP server: knowledge base, workflow builder, real-time execution, models, plugins.2stars

Devutilsofershap/mcp-server-devutilsDeveloper utilities MCP: base64, UUID, hash, JWT decode, cron, timestamps.2stars

OrgX MCP — Organizational Continuity for AI Agents

Tools

Readme

OrgX MCP — shared work context for AI agents

UI preview

Quickstart

Details

More from useorgx

Related Automation & Workflows MCP servers