MCP Tools Reference

This page documents all 65 tools available through the OrgX MCP server, organized by category.

This reference is auto-generated from the MCP server source code and the discovery-first routing aliases used by public MCP clients. To regenerate: pnpm docs:generate

Tool Catalog Overview

Category	Tools	Description
Recommended Entry Points	5	`orgx_decide`, `orgx_spawn`, `orgx_search`, …
Decisions	4	`orgx_decide`, `get_decision_history`, `orgx_decide`, …
Agents	4	`orgx_spawn`, `orgx_spawn`, `orgx_recommend`, …
Memory	1	`orgx_search`
Initiative Monitoring	1	`orgx_recommend`
Entity Management	11	`batch_create_entities`, `batch_delete_entities`, `comment_on_entity`, …
Organization	1	`orgx_recommend`
Planning	5	`orgx_plan`, `get_active_sessions`, `orgx_plan`, …
Scoring & Queue	2	`get_scoring_signals`, `orgx_recommend`
Streams	2	`get_initiative_stream_state`, `update_stream_progress`
Client Integration	6	`orgx_spawn`, `orgx_spawn`, `orgx_apply_changeset`, …
Workspace	1	`workspace`
Onboarding	1	`configure_org`
Stats	1	`stats`
Intelligence Flywheel	7	`orgx_recommend`, `get_my_trust_context`, `orgx_recommend`, …
Billing	3	`account_status`, `account_upgrade`, `account_usage_report`
Other	10	`get_decision_detail`, `get_job_timeline`, `get_logs`, …

Recommended Entry Points

5 tools for recommended entry points operations.

orgx_decide

Review agent decisions or work items awaiting human approval. Also known as: pending approvals, agent blocked, sign off, review decisions, approve AI work.

decision_id

string

Decision ID to approve or reject after user confirmation

action

string

Use list to review pending approvals, or approve/reject a specific decision_id Options: list, approve, reject.

note

string

Optional approval note

reason

string

Required rejection reason

limit

number

Maximum number of pending decisions to return when listing

urgency_filter

string

Optional urgency filter for the pending decision list Options: all, critical, high.

initiative_id

string

Optional initiative UUID to scope pending decisions

Required Scopes: decisions:read, decisions:write Profiles: memory Request:

{
  "tool": "orgx_decide",
  "args": {}
}

orgx_spawn

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.

agent

string

required

Target agent identifier or alias

task

string

required

Task instructions for the target agent

context

string

Optional supporting context or background for the task

initiative_id

string

Optional initiative UUID to associate with the spawned task

initiative_name

string

Optional initiative title to resolve automatically if ID is unknown

expected_artifacts

string[]

Optional final outputs you expect

deadline

string

Optional due date or plain-text deadline

style_guidelines

string

Optional voice, format, or style constraints

Required Scopes: agents:write Profiles: commander, executor, full Request:

{
  "tool": "orgx_spawn",
  "args": {
      "agent": "engineering-agent",
      "task": "task_value"
  }
}

orgx_search `read-only`

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.

query

string

required

Search query for organizational memory

scope

string

Optional scope filter for the memory search Options: all, artifacts, decisions, initiatives.

limit

number

Maximum number of results to return

Required Scopes: memory:read Profiles: memory Request:

{
  "tool": "orgx_search",
  "args": {
      "query": "pricing strategy"
  }
}

orgx_decide

Save a decision to organizational memory so agents and teammates can recall it later. Also known as: decision log, team memory, agent memory, record decision, remember what we decided.

decision

string

required

Decision text or short decision title to remember

context

string

Optional background, rationale, or source context

title

string

Optional explicit decision title

initiative_id

string

Optional parent initiative UUID

workspace_id

string

Workspace UUID

priority

string

Priority / urgency Options: low, medium, high, urgent.

Required Scopes: initiatives:write, memory:write Profiles: memory Request:

{
  "tool": "orgx_decide",
  "args": {
      "decision": "decision_value"
  }
}

orgx_recommend `read-only`

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.

initiative_id

string

Optional initiative UUID to check

initiative_name

string

Optional initiative title to resolve automatically if ID is unknown

Required Scopes: initiatives:read Profiles: memory Request:

{
  "tool": "orgx_recommend",
  "args": {}
}

Decisions

4 tools for decisions operations.

orgx_decide

Approve a specific pending OrgX decision after the user confirms. USE WHEN: user says to approve a decision returned from orgx_search with type=decision and status=pending (or the legacy orgx_decide alias). NEXT: Confirm approval to user; agent is notified automatically. DO NOT USE: without showing the decision to the user first. Requires decisions:write.

decision_id

string

required

note

string

option_id

string

Optional decision option id when the decision includes selectable options.

Required Scopes: decisions:write Profiles: commander Request:

{
  "tool": "orgx_decide",
  "args": {
      "decision_id": "dec_abc123"
  }
}

Response:

{
  "decision_id": "dec_abc123",
  "status": "approved",
  "artifact_id": "art_xyz789",
  "resolved_at": "2026-02-26T10:05:00Z"
}

get_decision_history `read-only`

Search past OrgX decisions related to a topic. USE WHEN: older clients still call this tool directly. NEXT: Present results with context; suggest orgx_decide or orgx_decide if relevant pending ones exist. DO NOT USE: for new prompts or skills. Read-only. Compatibility alias retained for older clients. Prefer orgx_search with scope=decisions with a topic query for new prompts, skills, and examples.

topic

string

required

initiative_id

string

limit

number

Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: commander, observer Request:

{
  "tool": "get_decision_history",
  "args": {
      "topic": "topic_value"
  }
}

Response:

{
  "decisions": [
    {
      "id": "dec_abc123",
      "type": "approval",
      "status": "approved",
      "resolved_by": "user_123",
      "resolved_at": "2026-02-26T10:05:00Z"
    }
  ],
  "total": 42,
  "cursor": "cur_next"
}

orgx_decide `read-only`

List OrgX decisions awaiting approval. USE WHEN: older clients still call this tool directly. NEXT: Present each decision with title and urgency, then ask which to orgx_decide or orgx_decide. DO NOT USE: for new prompts or skills. Read-only. Compatibility alias retained for older clients. Prefer orgx_search with type=decision and status=pending for new prompts, skills, and examples.

limit

number

Maximum number of decisions to return

urgency_filter

string

Options: all, critical, high.

initiative_id

string

Required Scopes: initiatives:read Profiles: commander, observer Request:

{
  "tool": "orgx_decide",
  "args": {}
}

Response:

{
  "decisions": [
    {
      "id": "dec_abc123",
      "type": "approval",
      "title": "Campaign brief ready for Q1 launch",
      "urgency": "high",
      "agent": "marketing-agent",
      "artifact_id": "art_xyz789",
      "created_at": "2026-02-26T10:00:00Z"
    }
  ],
  "total": 4,
  "cursor": null
}

orgx_decide

Reject a pending OrgX decision with a reason. 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.

decision_id

string

required

reason

string

required

option_id

string

Optional decision option id when the decision includes selectable options.

Required Scopes: decisions:write Profiles: commander Request:

{
  "tool": "orgx_decide",
  "args": {
      "decision_id": "dec_abc123",
      "reason": "Blocked by external dependency"
  }
}

Response:

{
  "decision_id": "dec_abc123",
  "status": "rejected",
  "resolved_at": "2026-02-26T10:05:00Z"
}

Agents

4 tools for agents operations.

orgx_spawn `read-only`

Show what OrgX agents are currently doing (running/idle). USE WHEN: user asks about agent activity, progress, or what agents are working on. NEXT: If agents are stuck, suggest orgx_decide or orgx_act. DO NOT USE: to check initiative health — use orgx_recommend instead. Read-only.

agent_id

string

include_idle

boolean

Required Scopes: initiatives:read Profiles: commander, observer Request:

{
  "tool": "orgx_spawn",
  "args": {}
}

Response:

{
  "agent_type": "engineering-agent",
  "status": "idle",
  "current_task_id": null,
  "completed_tasks": 12,
  "trust_level": "act_with_approval"
}

orgx_spawn

Hand a task to another agent, updating assignment and optionally spawning a new run. USE WHEN: a task needs to be reassigned to a different specialist agent. NEXT: Use orgx_spawn to confirm the new agent picked up the task. DO NOT USE: for new tasks — use orgx_spawn instead.

task_id

string

required

Task UUID to hand off

agent

string

required

Target agent (e.g., “engineering-agent”, “marketing-agent”)

note

string

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

spawn

boolean

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

Required Scopes: agents:write, initiatives:write Profiles: executor Request:

{
  "tool": "orgx_spawn",
  "args": {
      "task_id": "tsk_abc123",
      "agent": "engineering-agent"
  }
}

Response:

{
  "task_id": "tsk_abc123",
  "from_agent": "product-agent",
  "to_agent": "engineering-agent",
  "status": "handed_off"
}

orgx_recommend `read-only`

Recommend the next best action based on progress gaps and templates. USE WHEN: user asks what to do next, or needs help prioritizing. NEXT: Execute the recommended action (orgx_act, orgx_spawn, etc.). DO NOT USE: when user already knows what they want to do. Read-only.

entity_type

string

Entity type to recommend for (default: workspace) Options: workspace, initiative, workstream, milestone.

entity_id

string

Entity ID. For workspace, use “default” or a workspace ID.

workspace_id

string

Deprecated alias for workspace_id.

limit

number

Max recommendations to return (default 5, max 5)

cascade

boolean

If true, refresh recommendations across the entity chain first

Required Scopes: initiatives:read Profiles: commander, planner, observer Request:

{
  "tool": "orgx_recommend",
  "args": {}
}

Response:

{
  "recommendation": {
    "action": "orgx_decide",
    "target_id": "dec_abc123",
    "reasoning": "Campaign brief matches brand guidelines and has strong CTAs.",
    "confidence": 0.92
  }
}

orgx_spawn

Assign work to a specialist OrgX agent. Automatically checks authorization, rate limits, and quality gates before spawning. Returns modelTier and run details on success, or blockedReason if spawn is denied. USE WHEN: user explicitly wants to delegate work to an agent. NEXT: Use orgx_spawn to monitor progress. DO NOT USE: for creating tasks in the hierarchy — use orgx_write type=task instead. Requires agents:write.

agent

string

required

task

string

required

context

string

initiative_id

string

initiative_name

string

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

expected_artifacts

string[]

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

deadline

string

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

style_guidelines

string

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

wait_for_completion

boolean

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

execution_target

string

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

sdk_backend

string

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

model_tier

string

Model quality tier for this task. standard=fast/cheap (Haiku/GPT-nano), balanced=best trade-off (Sonnet/GPT-mini, default), precision=highest quality (Opus/GPT-4). Overrides the initiative’s default tier. Options: standard, balanced, precision.

Required Scopes: agents:write Profiles: executor Request:

{
  "tool": "orgx_spawn",
  "args": {
      "agent": "engineering-agent",
      "task": "task_value"
  }
}

Response:

{
  "task_id": "tsk_new123",
  "agent_type": "engineering-agent",
  "status": "queued",
  "estimated_start": "2026-02-26T10:10:00Z"
}

Memory

1 tool for memory operations.

orgx_search `read-only`

Search OrgX organizational memory (decisions, initiatives, artifacts) for a query. USE WHEN: user asks about past decisions, context, or knowledge. NEXT: Present relevant results; suggest drill-down with orgx_search. Prefer orgx_search with scope=decisions with a topic query for new prompts, skills, and examples. DO NOT USE: for listing current entities — use orgx_search instead. Read-only.

query

string

required

scope

string

Options: all, artifacts, decisions, initiatives.

limit

number

Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: commander, planner, observer Request:

{
  "tool": "orgx_search",
  "args": {
      "query": "pricing strategy"
  }
}

Response:

{
  "results": [
    {
      "type": "artifact",
      "id": "art_xyz789",
      "title": "Q1 Campaign Brief",
      "relevance": 0.95,
      "snippet": "Launch messaging for the Q1 product update..."
    }
  ],
  "total": 3
}

Initiative Monitoring

1 tool for initiative monitoring operations.

orgx_recommend `read-only`

Get health, milestones, blockers, and recent activity for a single initiative. USE WHEN: user asks how an initiative is going, or wants a status update. NEXT: If blockers exist, suggest orgx_act to resolve. For deeper drill-down, use orgx_search with initiative_id. DO NOT USE: for org-wide overview — use orgx_recommend instead. Read-only.

initiative_id

string

Optional: Initiative UUID to check.

initiative_name

string

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

Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: commander, planner, observer Request:

{
  "tool": "orgx_recommend",
  "args": {}
}

Response:

{
  "initiative_id": "init_abc123",
  "health": "on_track",
  "progress": 0.65,
  "active_workstreams": 3,
  "blocked_tasks": 0,
  "pending_decisions": 1,
  "last_activity": "2026-02-26T09:30:00Z"
}

Entity Management

11 tools for entity management operations.

batch_create_entities

Create multiple entities in one call with ref-based dependency resolution. No parameters required. Required Scopes: initiatives:write Profiles: planner Request:

{
  "tool": "batch_create_entities",
  "args": {}
}

Response:

{
  "created": [
    {
      "ref": "task1",
      "id": "tsk_aaa",
      "type": "task"
    },
    {
      "ref": "task2",
      "id": "tsk_bbb",
      "type": "task"
    }
  ],
  "total": 2
}

batch_delete_entities

Delete multiple entities in one call. Supports cascade and force options.

ids

string[]

required

Entity IDs to delete

cascade

boolean

Also delete child entities

force

boolean

Force delete even if entity has active children

Required Scopes: initiatives:write Profiles: all Request:

{
  "tool": "batch_delete_entities",
  "args": {
      "ids": []
  }
}

Response:

{
  "deleted": [
    "tsk_aaa",
    "tsk_bbb"
  ],
  "total": 2
}

comment_on_entity

Leave a threaded comment on an entity for annotations, concerns, or progress notes.

entity_id

string

required

Entity ID to comment on

body

string

required

Comment body (markdown supported)

parent_comment_id

string

Reply to a specific comment

Required Scopes: initiatives:write Profiles: commander, executor Request:

{
  "tool": "comment_on_entity",
  "args": {
      "entity_id": "ent_abc123",
      "body": "This is looking great!"
  }
}

Response:

{
  "comment_id": "cmt_abc123",
  "entity_id": "tsk_abc123",
  "body": "Looking good so far!",
  "created_at": "2026-02-26T10:00:00Z"
}

orgx_write

Create a new entity of any type. For full initiative hierarchies, use scaffold_initiative instead. No parameters required. Required Scopes: initiatives:write Profiles: commander, planner Request:

{
  "tool": "orgx_write",
  "args": {}
}

Response:

{
  "id": "tsk_new456",
  "type": "task",
  "title": "Design hero section",
  "status": "pending",
  "parent_id": "ws_abc123",
  "created_at": "2026-02-26T10:00:00Z"
}

orgx_act

Perform lifecycle actions on any entity (launch, pause, complete, etc.). Use action=list_actions to discover available actions.

type

string

required

Entity type Options: initiative, milestone, workstream, task, objective, playbook, decision, stream, studio_content.

string

required

Entity ID

action

string

Action to perform (launch, pause, complete, etc.). Omit to list available actions.

force

boolean

Force the action even if preconditions are not met.

note

string

Optional note attached to the action.

Required Scopes: initiatives:write Profiles: commander, planner, executor Request:

{
  "tool": "orgx_act",
  "args": {
      "type": "initiative",
      "id": "id_value"
  }
}

Response:

{
  "id": "init_abc123",
  "type": "initiative",
  "action": "launch",
  "previous_status": "pending",
  "new_status": "active",
  "timestamp": "2026-02-26T10:00:00Z"
}

orgx_inspect `read-only`

Fetch a task with hydrated context attachments (entities, artifacts, plan sessions).

task_id

string

required

Task ID

Required Scopes: initiatives:read Profiles: commander, planner, executor, observer Request:

{
  "tool": "orgx_inspect",
  "args": {
      "task_id": "tsk_abc123"
  }
}

Response:

{
  "task": {
    "id": "tsk_abc123",
    "title": "Build hero section",
    "status": "in_progress"
  },
  "parent": {
    "id": "ws_001",
    "type": "workstream",
    "title": "Frontend"
  },
  "initiative": {
    "id": "init_abc123",
    "title": "Q1 Product Launch"
  },
  "artifacts": [],
  "comments": []
}

orgx_search `read-only`

List entities of any type with filters and pagination. Supported types: workspace, project, initiative, milestone, workstream, task, objective, playbook, decision, artifact, run, blocker, workflow, agent, skill, plan_session, stream, studio_brand, studio_content, video_template.

type

string

required

Entity type to list Options: workspace, project, initiative, milestone, workstream, task, objective, playbook, decision, artifact, run, blocker, workflow, agent, skill, plan_session, stream, studio_brand, studio_content, video_template.

limit

number

Max results (default: 20, max: 100).

cursor

string

Pagination cursor.

status

string

Filter by status.

parent_id

string

Filter by parent entity ID.

string

Fetch a single entity by ID (with hydrated context when hydrate_context=true).

hydrate_context

boolean

Include relationships and rich context.

include_relationships

boolean

Include related entities.

Required Scopes: initiatives:read Profiles: commander, planner, executor, observer Request:

{
  "tool": "orgx_search",
  "args": {
      "type": "workspace"
  }
}

Response:

{
  "entities": [
    {
      "id": "init_abc123",
      "type": "initiative",
      "title": "Q1 Product Launch",
      "status": "active",
      "created_at": "2026-01-15T00:00:00Z"
    }
  ],
  "total": 3,
  "cursor": null
}

list_entity_comments `read-only`

List comments for an entity. Returns threaded discussion.

entity_id

string

required

Entity ID

limit

number

Max comments to return

Required Scopes: initiatives:read Profiles: commander, observer Request:

{
  "tool": "list_entity_comments",
  "args": {
      "entity_id": "ent_abc123"
  }
}

Response:

{
  "comments": [
    {
      "id": "cmt_abc123",
      "body": "Looking good!",
      "author": "user_123",
      "created_at": "2026-02-26T10:00:00Z"
    }
  ],
  "total": 1
}

scaffold_initiative

Create a complete initiative with workstreams, milestones, and tasks in one call.

title

string

required

Initiative title

summary

string

Initiative summary

workstreams

object[]

Workstream definitions with nested tasks

milestones

object[]

Milestone definitions

auto_launch

boolean

Auto-launch initiative after creation (default: true)

Required Scopes: initiatives:write Profiles: commander, planner Request:

{
  "tool": "scaffold_initiative",
  "args": {
      "title": "Q1 Product Launch"
  }
}

Response:

{
  "initiative": {
    "id": "init_new789",
    "title": "Q1 Product Launch",
    "status": "active"
  },
  "workstreams": [
    {
      "id": "ws_001",
      "title": "Frontend"
    }
  ],
  "milestones": [
    {
      "id": "ms_001",
      "title": "Beta launch"
    }
  ],
  "tasks": [
    {
      "id": "tsk_001",
      "title": "Build hero section"
    }
  ],
  "total_entities_created": 5
}

update_entity

Update entity fields (title, description, metadata). For status changes, use orgx_act. No parameters required. Required Scopes: initiatives:write Profiles: commander, planner Request:

{
  "tool": "update_entity",
  "args": {}
}

Response:

{
  "id": "tsk_abc123",
  "type": "task",
  "title": "Updated title",
  "updated_at": "2026-02-26T10:00:00Z"
}

orgx_act dry_run=true `read-only`

Run pre-completion verification to confirm all child work is done before completing an entity.

type

string

required

Entity type Options: initiative, milestone, workstream, task, objective, playbook, decision, stream, studio_content.

string

required

Entity ID

Required Scopes: initiatives:read Profiles: commander Request:

{
  "tool": "orgx_act",
  "args": {
    "dry_run": true,
    "type": "initiative",
    "id": "id_value"
  }
}

Response:

{
  "id": "init_abc123",
  "can_complete": false,
  "blockers": [
    {
      "type": "task",
      "id": "tsk_xyz",
      "title": "Pending review",
      "status": "in_progress"
    }
  ]
}

Organization

1 tool for organization operations.

orgx_recommend `read-only`

Fetch a compact organization snapshot. Returns org-wide overview of initiatives, progress, and health.

view

string

Response view mode (default: summary). Options: summary, detailed.

initiative_status

string

Filter initiatives by status. Options: active, paused, all.

include

string[]

Detailed mode payload sections.

limit

number

Max initiatives to return (default: 20, max: 100).

cursor

string

Pagination cursor from a previous result.

Required Scopes: initiatives:read Profiles: commander, observer Request:

{
  "tool": "orgx_recommend",
  "args": {}
}

Response:

{
  "workspace": "My Startup",
  "initiatives": {
    "total": 3,
    "active": 2,
    "completed": 1
  },
  "pending_decisions": 4,
  "active_agents": 2,
  "recent_artifacts": 7
}

Planning

5 tools for planning operations.

orgx_plan

Mark a plan as complete and record implementation details. USE WHEN: user finishes building the planned feature. NEXT: Optionally attach to entities via attach_to. DO NOT USE: if the plan session is still in progress.

session_id

string

required

Plan session ID

implementation_summary

string

Summary of what was built

files_changed

string[]

List of files modified

deviations

object[]

Any deviations from the plan

attach_to

object[]

Optional: attach this plan session as context on target entities (pointers, not payloads).

Required Scopes: decisions:write Profiles: planner Request:

{
  "tool": "orgx_plan",
  "args": {
      "session_id": "ps_abc123"
  }
}

Response:

{
  "session_id": "ps_abc123",
  "status": "completed",
  "entities_created": 8,
  "completed_at": "2026-02-26T10:10:00Z"
}

get_active_sessions `read-only`

Check for any active planning sessions you have open. USE WHEN: resuming a conversation or checking if a plan session exists. NEXT: Continue with orgx_plan or orgx_plan. Read-only. No parameters required. Required Scopes: initiatives:read Profiles: planner Request:

{
  "tool": "get_active_sessions",
  "args": {}
}

Response:

{
  "sessions": [
    {
      "id": "ps_abc123",
      "initiative_id": "init_abc123",
      "status": "active",
      "created_at": "2026-02-26T10:00:00Z"
    }
  ]
}

orgx_plan

Get AI suggestions to improve your plan based on past patterns and best practices. USE WHEN: user wants feedback on a plan draft. NEXT: Apply suggestions via orgx_plan. DO NOT USE: without an active plan session — call orgx_plan first.

session_id

string

required

Plan session ID

plan_content

string

required

Current plan content to analyze

Required Scopes: decisions:write Profiles: planner Request:

{
  "tool": "orgx_plan",
  "args": {
      "session_id": "ps_abc123",
      "plan_content": "plan_content_value"
  }
}

Response:

{
  "session_id": "ps_abc123",
  "suggestions": [
    {
      "type": "add_task",
      "workstream": "Frontend",
      "title": "Add responsive breakpoints",
      "reasoning": "Mobile traffic accounts for 60% of visits."
    }
  ]
}

orgx_plan

Record an edit made to a plan to learn planning patterns. USE WHEN: user modifies their plan during a session. NEXT: Continue editing or call orgx_plan for more suggestions. DO NOT USE: without an active plan session.

session_id

string

required

Plan session ID

edit_type

string

required

Type of edit made Options: add_section, remove_section, modify_section, add_detail, change_approach, add_edge_case, add_constraint, reorder, other.

before_content

string

Content before edit

after_content

string

required

Content after edit

section_path

string

Section path like ”## API Design”

user_reason

string

Why this edit was made

Required Scopes: decisions:write Profiles: planner Request:

{
  "tool": "orgx_plan",
  "args": {
      "session_id": "ps_abc123",
      "edit_type": "add_section",
      "after_content": "after_content_value"
  }
}

Response:

{
  "session_id": "ps_abc123",
  "edit_id": "ed_001",
  "recorded_at": "2026-02-26T10:05:00Z"
}

orgx_plan

Start a new planning session to track your feature plan. USE WHEN: user begins planning a new feature or initiative. NEXT: Use orgx_plan for suggestions, orgx_plan to track changes, orgx_plan when done. DO NOT USE: for creating initiative hierarchies — use scaffold_initiative instead.

feature_name

string

required

Name of the feature being planned

initial_plan

string

Initial plan content if any

Required Scopes: decisions:write Profiles: planner Request:

{
  "tool": "orgx_plan",
  "args": {
      "feature_name": "feature_name_value"
  }
}

Response:

{
  "session_id": "ps_abc123",
  "initiative_id": "init_abc123",
  "status": "active",
  "created_at": "2026-02-26T10:00:00Z"
}

Scoring & Queue

2 tools for scoring & queue operations.

get_scoring_signals `read-only`

Show raw signal data (blocking decisions, stream conflicts, health, budget, critical path, quality) for scoring. USE WHEN: user wants to understand why items are ranked the way they are in orgx_recommend. NEXT: Adjust with set_scoring_weights if weights need tuning. Read-only.

initiative_id

string

required

Initiative UUID to gather signals for

workstream_id

string

Optional: filter to a specific workstream

Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: all Request:

{
  "tool": "get_scoring_signals",
  "args": {
      "initiative_id": "init_abc123"
  }
}

Response:

{
  "signals": [
    {
      "name": "urgency",
      "weight": 0.3,
      "description": "Time sensitivity based on deadlines"
    },
    {
      "name": "impact",
      "weight": 0.25,
      "description": "Business value"
    }
  ]
}

orgx_recommend `read-only`

Run the composite scoring engine and return ranked queue items with factor breakdowns. USE WHEN: older clients explicitly need raw queue scoring output. NEXT: Execute the top-ranked item via orgx_act or orgx_spawn. DO NOT USE: for new prompts or skills. Read-only. Compatibility alias retained for older clients. Prefer orgx_recommend with workspace or initiative recommendations for new prompts, skills, and examples.

initiative_id

string

Initiative UUID to score

workspace_id

string

Deprecated alias for workspace_id.

limit

number

Max items to return (default 10)

Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: commander, observer Request:

{
  "tool": "orgx_recommend",
  "args": {}
}

Response:

{
  "queue": [
    {
      "entity_id": "tsk_abc123",
      "score": 92,
      "signals": {
        "urgency": 30,
        "impact": 25,
        "recency": 20,
        "dependency": 17
      }
    }
  ],
  "scored_at": "2026-02-26T10:00:00Z"
}

Streams

2 tools for streams operations.

get_initiative_stream_state `read-only`

Get aggregate stream state for an initiative including overall progress, blockers, and computed metrics. USE WHEN: checking stream execution status for an initiative. NEXT: If streams are blocked, use orgx_act to unblock. DO NOT USE: for raw stream records — use orgx_search type=stream instead. Read-only.

initiative_id

string

required

The initiative ID

Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: executor, observer Request:

{
  "tool": "get_initiative_stream_state",
  "args": {
      "initiative_id": "init_abc123"
  }
}

Response:

{
  "initiative_id": "init_abc123",
  "streams": [
    {
      "id": "str_abc123",
      "workstream": "Frontend",
      "progress": 0.75,
      "status": "active"
    }
  ]
}

update_stream_progress

Report progress and confidence on a stream with velocity tracking. USE WHEN: agent is actively working a stream and needs to report progress. NEXT: Continue work; call again at each meaningful progress change. DO NOT USE: for general entity status changes — use orgx_act instead.

stream_id

string

required

The stream ID to update

progress_pct

number

Progress percentage (0-100)

confidence

number

Confidence level (0-1) - separate from progress

status_note

string

Brief note about current status

expected_version

number

For optimistic locking

Required Scopes: agents:write Profiles: executor Request:

{
  "tool": "update_stream_progress",
  "args": {
      "stream_id": "stream_id_value"
  }
}

Response:

{
  "stream_id": "str_abc123",
  "progress": 0.75,
  "updated_at": "2026-02-26T10:00:00Z"
}

Client Integration

6 tools for client integration operations.

orgx_spawn

Check whether an agent spawn is allowed before executing. Returns model tier, rate limit status, quality gate, and task verification. USE WHEN: before any orgx_spawn call. NEXT: If allowed, proceed with orgx_spawn using the returned model tier. If blocked, inform user of the reason.

domain

string

required

Agent domain: engineering, marketing, product, design, ops, sales, orchestration

task_id

string

OrgX task ID this spawn is for

task_title

string

Task title (for model routing if task_id not provided)

task_description

string

Task description

Required Scopes: agents:write Profiles: all Request:

{
  "tool": "orgx_spawn",
  "args": {
      "domain": "domain_value"
  }
}

Response:

{
  "allowed": true,
  "trust_level": "act_with_approval",
  "budget_remaining_usd": 4.5
}

orgx_spawn `read-only`

Classify a task and get the recommended model tier (opus for planning/architecture, sonnet for execution, local for routine). USE WHEN: deciding which model to use for agent work. NEXT: Use the returned tier when spawning via orgx_spawn. Read-only.

title

string

required

Task title

description

string

Task description

entity_type

string

Entity type: task, decision, initiative

domain

string

Agent domain

Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: all Request:

{
  "tool": "orgx_spawn",
  "args": {
      "title": "Q1 Product Launch"
  }
}

Response:

{
  "task_id": "tsk_abc123",
  "recommended_model": "claude-sonnet-4-6",
  "reasoning": "Standard complexity task with clear requirements."
}

orgx_apply_changeset

Apply an idempotent transactional changeset for task/milestone/decision mutations. USE WHEN: agent needs to create/update multiple tasks, milestones, or decisions atomically. NEXT: Call orgx_emit_activity to log what was changed. DO NOT USE: for single entity updates — use orgx_act or update_entity instead.

initiative_id

string

required

Initiative UUID

idempotency_key

string

required

Idempotency key for safe retries

operations

object[]

required

run_id

string

Existing run UUID

correlation_id

string

Required when run_id is not provided

source_client

string

Required when run_id is not provided Options: openclaw, codex, claude-code, api.

Required Scopes: Authenticated user Profiles: executor Request:

{
  "tool": "orgx_apply_changeset",
  "args": {
      "initiative_id": "init_abc123",
      "idempotency_key": "idempotency_key_value",
      "operations": []
  }
}

Response:

{
  "applied": true,
  "changeset_id": "cs_abc123",
  "entities_affected": 3
}

orgx_emit_activity

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 orgx_act instead. No parameters required. Required Scopes: Authenticated user Profiles: executor Request:

{
  "tool": "orgx_emit_activity",
  "args": {}
}

Response:

{
  "emitted": true,
  "activity_id": "act_abc123"
}

record_quality_score

Record a quality score (1-5) for a completed agent task. Scores feed into the quality gate — low-scoring domains get throttled. USE WHEN: after reviewing agent output. NEXT: Scores affect future orgx_spawn decisions. DO NOT USE: for in-progress tasks — wait until completion.

task_id

string

required

OrgX task ID

agent_domain

string

required

Agent domain that completed the task

score

number

required

Quality score: 1=poor, 3=acceptable, 5=excellent

scored_by

string

Who scored this Options: human, auto, peer.

notes

string

Notes on the score

Required Scopes: decisions:write Profiles: commander Request:

{
  "tool": "record_quality_score",
  "args": {
      "task_id": "tsk_abc123",
      "agent_domain": "agent_domain_value",
      "score": 10
  }
}

Response:

{
  "recorded": true,
  "entity_id": "tsk_abc123",
  "score": 0.88
}

sync_client_state

Sync local memory with OrgX. Push decisions/logs, pull active context. USE WHEN: at session start and periodically during long sessions. NEXT: Review returned initiatives and pending decisions, ask user what to focus on. USE BEFORE: spawning agent work, to ensure latest state.

memory

string

Local MEMORY.md content to push

daily_log

string

Today’s session log to push

Required Scopes: Authenticated user Profiles: executor Request:

{
  "tool": "sync_client_state",
  "args": {}
}

Response:

{
  "synced": true,
  "last_sync": "2026-02-26T10:00:00Z",
  "pending_changes": 0
}

Workspace

1 tool for workspace operations.

workspace

List, get, or set the active workspace. USE WHEN: user wants to see their workspaces, check which is active, or switch workspaces. action=list to see all, action=get for current, action=set to switch.

action

string

required

list=show all, get=current, set=switch active Options: list, get, set.

workspace_id

string

Workspace UUID to switch to (action=set only)

Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: commander, planner, executor, observer Request:

{
  "tool": "workspace",
  "args": {
      "action": "list"
  }
}

Response:

{
  "workspace_id": "ws_abc123",
  "name": "My Startup",
  "plan": "team",
  "created_at": "2025-10-01T00:00:00Z"
}

Onboarding

1 tool for onboarding operations.

configure_org

Check setup status, configure agents, or set org policies. USE WHEN: first connecting, onboarding, or adjusting agent/policy settings. action=status for progress, action=configure_agent to set agent preferences, action=set_policy for org-wide rules. No parameters required. Required Scopes: initiatives:read Profiles: commander Request:

{
  "tool": "configure_org",
  "args": {}
}

Response:

{
  "workspace_id": "ws_abc123",
  "steps": {
    "linear_connected": true,
    "github_connected": false,
    "first_initiative": true,
    "first_decision": false
  },
  "completion": 0.5
}

Stats

1 tool for stats operations.

stats `read-only`

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

scope

string

required

personal=your stats, session=current session diagnostics Options: personal, session. Default: "personal".

timeframe

string

Time period for stats (personal only) Options: today, week, month, all_time.

Required Scopes: initiatives:read Profiles: commander, observer Request:

{
  "tool": "stats",
  "args": {
      "scope": "personal"
  }
}

Response:

{
  "period": "30d",
  "decisions_resolved": 42,
  "artifacts_shipped": 18,
  "agents_spawned": 7,
  "avg_decision_time_hours": 2.3
}

Intelligence Flywheel

7 tools for intelligence flywheel operations.

orgx_recommend `read-only`

Returns the morning brief: curated receipts, exceptions, ROI delta, and value signals from the most recent autonomous session. Defaults to the most recent session if no session ID is provided. Prefer orgx_recommend with workspace brief with value and exception summaries for new prompts, skills, and examples.

workspace_id

string

required

Workspace ID

session_id

string

Specific session ID (defaults to most recent)

Required Scopes: initiatives:read Profiles: all Request:

{
  "tool": "orgx_recommend",
  "args": {
      "workspace_id": "ws_abc123"
  }
}

Response:

{
  "session_id": "auto_abc123",
  "summary": "7 tasks completed, 2 decisions pending review",
  "tasks_completed": 7,
  "decisions_created": 2,
  "total_cost_usd": 2.15,
  "artifacts": [
    "art_001",
    "art_002"
  ]
}

get_my_trust_context `read-only`

Agent-facing: “What’s my trust level per capability? What do I need for promotion? Which receipts are helping/hurting?” Returns the full trust context for an agent including levels, scores, thresholds, and recent trust events.

workspace_id

string

required

Workspace ID

agent_type

string

required

Agent type to query trust for

Required Scopes: agents:read Profiles: all Request:

{
  "tool": "get_my_trust_context",
  "args": {
      "workspace_id": "ws_abc123",
      "agent_type": "engineering-agent"
  }
}

Response:

{
  "agent_type": "engineering-agent",
  "trust_level": "act_with_approval",
  "capabilities": {
    "read_code": "autonomous",
    "create_pr": "act_with_approval",
    "merge_pr": "draft"
  },
  "promotion_progress": 0.7
}

orgx_recommend `read-only`

ROI summary from the economic ledger. Human: “3.2x ROI this month.” Agent: “My outreach_draft receipts average $0.26 attributed value.” Returns cost/value/ROI breakdowns by agent, capability, and time period. Compatibility alias retained for older clients. Prefer orgx_recommend with workspace brief with value and exception summaries for new prompts, skills, and examples.

workspace_id

string

required

Workspace ID

period

string

required

Time period for ROI calculation Options: 7d, 30d, 90d. Default: "30d".

agent_type

string

Filter by specific agent type

capability_key

string

Filter by capability key

Required Scopes: initiatives:read Profiles: all Request:

{
  "tool": "orgx_recommend",
  "args": {
      "workspace_id": "ws_abc123",
      "period": "7d"
  }
}

Response:

{
  "outcomes": [
    {
      "entity_id": "tsk_abc123",
      "cost_usd": 0.12,
      "value_attributed": "high",
      "receipt_id": "rcp_abc123"
    }
  ],
  "total_cost_usd": 3.45,
  "period": "30d"
}

get_relevant_learnings `read-only`

Agent-facing: “What has the org learned about my capability?” Returns ranked org learnings relevant to a specific capability or task context.

workspace_id

string

required

Workspace ID

capability_key

string

Capability key to filter learnings

keywords

string[]

Keywords for semantic matching

limit

integer

required

Default: 5.

Required Scopes: memory:read Profiles: all Request:

{
  "tool": "get_relevant_learnings",
  "args": {
      "workspace_id": "ws_abc123",
      "limit": 10
  }
}

Response:

{
  "learnings": [
    {
      "id": "lrn_abc123",
      "pattern": "Auth bugs often stem from token refresh race conditions",
      "source_task": "tsk_xyz",
      "confidence": 0.85
    }
  ]
}

record_outcome

Record a business outcome (deal closed, meeting booked, cycle time reduced). Agents can self-report outcomes they detect. Triggers attribution inference to connect outcomes to receipts. No parameters required. Required Scopes: initiatives:write Profiles: all Request:

{
  "tool": "record_outcome",
  "args": {}
}

Response:

{
  "outcome_id": "out_abc123",
  "entity_id": "tsk_abc123",
  "recorded_at": "2026-02-26T10:00:00Z"
}

start_autonomous_session

Start an autonomous execution session with budget guardrails. Human: “Run overnight with $5 budget.” Creates a session that produces receipts while executing eligible work items.

workspace_id

string

required

Workspace ID

session_type

string

required

Options: overnight, weekend, scheduled, manual. Default: "manual".

max_cost_usd

number

required

Maximum budget in USD (hard stop — zero tolerance) Default: 5.

max_receipts

integer

required

Maximum number of receipts to produce Default: 50.

allowed_trust_levels

string[]

required

Only execute capabilities at these trust levels Default: ["autonomous","act_with_approval"].

Required Scopes: agents:write Profiles: all Request:

{
  "tool": "start_autonomous_session",
  "args": {
      "workspace_id": "ws_abc123",
      "session_type": "overnight",
      "max_cost_usd": 10,
      "max_receipts": "max_receipts_value",
      "allowed_trust_levels": []
  }
}

Response:

{
  "session_id": "auto_abc123",
  "max_cost_usd": 5,
  "max_receipts": 50,
  "started_at": "2026-02-26T22:00:00Z"
}

submit_learning

Agent-facing: Submit a discovery or insight as an org learning. Enters org_learnings after confidence validation. One agent’s discovery benefits all agents.

workspace_id

string

required

Workspace ID

learning_type

string

required

Type of learning Options: failure_pattern, success_pattern, cost_optimization, quality_heuristic.

summary

string

required

Human-readable learning summary

capability_key

string

Applicable capability key

evidence_receipt_ids

string[]

Receipt IDs that support this learning

keywords

string[]

Semantic keywords for matching

Required Scopes: memory:read Profiles: all Request:

{
  "tool": "submit_learning",
  "args": {
      "workspace_id": "ws_abc123",
      "learning_type": "failure_pattern",
      "summary": "summary_value"
  }
}

Response:

{
  "learning_id": "lrn_new123",
  "submitted_at": "2026-02-26T10:00:00Z",
  "status": "accepted"
}

Billing

3 tools for billing operations.

account_status `read-only`

Returns account tier, usage, and current edge rate-limit allowance.

user_id

string

Optional user ID override.

Required Scopes: Authenticated user Profiles: all Request:

{
  "tool": "account_status",
  "args": {}
}

Response:

{
  "user_id": "usr_abc123",
  "plan": "free",
  "tier": "free",
  "rate_limit_status": {
    "window": "1h",
    "limit_per_hour": 100,
    "remaining": 92
  }
}

account_upgrade

Starts an account upgrade flow and returns checkout/contact URL.

target_plan

string

Target plan to upgrade to. Options: pro, enterprise.

billing_cycle

string

Billing cycle preference. Options: monthly, annual.

user_id

string

Optional user ID override.

Required Scopes: Authenticated user Profiles: all Request:

{
  "tool": "account_upgrade",
  "args": {}
}

Response:

{
  "target_plan": "pro",
  "billing_cycle": "monthly",
  "checkout_url": "https://checkout.stripe.com/c/pay/cs_abc123"
}

account_usage_report `read-only`

Returns billing usage details with current edge rate-limit usage.

user_id

string

Optional user ID override.

Required Scopes: Authenticated user Profiles: all Request:

{
  "tool": "account_usage_report",
  "args": {}
}

Response:

{
  "user_id": "usr_abc123",
  "plan": "free",
  "usage": {
    "creditsUsed": 15,
    "creditsIncluded": 100
  },
  "edge_rate_limit": {
    "window": "1h",
    "limit_per_hour": 100,
    "remaining": 92
  }
}

Other

10 tools for other operations.

get_decision_detail `read-only`

Get one decision with its structured interaction steps, options, questions, config requirements, evidence, and comments. USE WHEN: the UI needs to render a guided decision review instead of a simple approve/reject action.

decision_id

string

required

comments_cursor

string

Optional pagination cursor for additional comments.

comments_limit

number

Optional maximum comments to load.

Required Scopes: initiatives:read Profiles: all Request:

{
  "tool": "get_decision_detail",
  "args": {
      "decision_id": "dec_abc123"
  }
}

get_job_timeline

Fetch background job and tool-job timeline events for a run or job. USE WHEN: diagnosing queueing, retries, dispatch, or completion order.

job_id

string

Specific job ID

run_id

string

Run ID to list related jobs

Required Scopes: initiatives:read Profiles: all Request:

{
  "tool": "get_job_timeline",
  "args": {}
}

get_logs

Fetch correlated logs for a run or trace. USE WHEN: you need live log lines from Loki filtered by run, trace, service, or query.

run_id

string

Run ID filter

trace_id

string

Trace ID filter

query

string

Free-text filter

service

string

Service name filter

since

string

Optional ISO timestamp

limit

integer

Required Scopes: initiatives:read Profiles: all Request:

{
  "tool": "get_logs",
  "args": {}
}

get_run_debug_bundle

Fetch a normalized live debug bundle for a run. USE WHEN: debugging a run and you need trace, logs, jobs, sessions, and sandbox state in one read-only payload. NEXT: Drill deeper with get_trace, get_logs, get_job_timeline, or get_session_state.

run_id

string

required

OrgX run ID

include

string[]

Optional sections to include. Defaults to trace, logs, jobs, sessions, and sandbox.

since

string

Optional ISO timestamp or backend-supported relative time

Required Scopes: initiatives:read Profiles: all Request:

{
  "tool": "get_run_debug_bundle",
  "args": {
      "run_id": "run_id_value"
  }
}

get_session_state

Fetch normalized run/session/provider/sandbox session state. USE WHEN: debugging continuity, reconnects, provider session mapping, or sandbox session status.

session_id

string

Responses/session ID

provider_session_id

string

Provider-native session ID

sandbox_session_id

string

Sandbox session ID

run_id

string

Run ID

Required Scopes: initiatives:read Profiles: all Request:

{
  "tool": "get_session_state",
  "args": {}
}

get_trace

Fetch a normalized trace summary and simplified span list. USE WHEN: you have a trace_id or run_id and need live trace data from Tempo rather than reconstructing from the database.

trace_id

string

Trace ID to fetch directly

run_id

string

Run ID to resolve to a trace

since

string

Optional search window when resolving by run ID

Required Scopes: initiatives:read Profiles: all Request:

{
  "tool": "get_trace",
  "args": {}
}

queue_action

Pin, unpin, or skip a workstream in the Next Up queue. USE WHEN: user wants to force-prioritize or deprioritize a workstream. action=pin to force-top, action=unpin to remove pin, action=skip to temporarily deprioritize. Requires initiatives:write.

action

string

required

Queue operation Options: pin, unpin, skip.

initiative_id

string

required

Initiative UUID

workstream_id

string

required

Workstream UUID

workspace_id

string

Deprecated alias for workspace_id

rank

number

Position among pinned items, 0=top (pin only)

duration_minutes

number

Skip duration in minutes, default 60, max 10080 (skip only)

Required Scopes: initiatives:write Profiles: commander Request:

{
  "tool": "queue_action",
  "args": {
      "action": "pin",
      "initiative_id": "init_abc123",
      "workstream_id": "ws_abc123"
  }
}

resolve_decision

Resolve a decision using the structured interaction outcome contract. USE WHEN: a user completes a guided decision review that may include option selection, questions, surfaces, config completion, or subrequest updates.

decision_id

string

required

status

string

required

Options: approved, declined, cancelled.

summary

string

note

string

option_id

string

answers

object

surface_ids

string[]

surfaces

object[]

config_session_id

string

subrequest_updates

object[]

final_step_id

string

Required Scopes: decisions:write Profiles: all Request:

{
  "tool": "resolve_decision",
  "args": {
      "decision_id": "dec_abc123",
      "status": "approved"
  }
}

save_decision_draft

Save partial progress for a structured decision review. USE WHEN: the user has started a multi-step decision and the surface needs to persist the current step, answers, option selection, or subrequest state without resolving it.

decision_id

string

required

current_step_id

string

selected_option_id

string

answers

object

note

string

surface_ids

string[]

config_session_id

string

subrequest_updates

object[]

updated_at

string

Required Scopes: decisions:write Profiles: all Request:

{
  "tool": "save_decision_draft",
  "args": {
      "decision_id": "dec_abc123"
  }
}

scoring_config

Read or update scoring engine configuration. USE WHEN: user asks about scoring setup, wants to toggle scoring, adjust weights, or change active signals. action=get to read, action=update to modify. NEXT: Run orgx_recommend to see effects in the preferred workflow, or orgx_recommend if you need raw queue scoring. Read-only for get, requires initiatives:write for update. No parameters required. Required Scopes: decisions:read, agents:read, initiatives:read, memory:read Profiles: commander, observer Request:

{
  "tool": "scoring_config",
  "args": {}
}

Deprecated Tools

The following tools are deprecated and will be removed in a future version. Migrate to the recommended replacements.

Deprecated Tool	Replacement	Migration Note
`create_initiative`	orgx_write type=initiative (or scaffold_initiative for full hierarchy)	The create_initiative tool has been replaced by the generic entity system.
`list_initiatives`	orgx_search type=initiative	The list_initiatives tool has been replaced by the generic entity system.
`orgx_write`	orgx_write type=milestone	The orgx_write tool has been replaced by the generic entity system.
`orgx_write`	orgx_write type=task	The orgx_write tool has been replaced by the generic entity system.
`launch_entity`	orgx_act action=launch	The launch_entity tool has been replaced by the unified orgx_act tool.
`pause_entity`	orgx_act action=pause	The pause_entity tool has been replaced by the unified orgx_act tool.
`complete_entity`	orgx_act action=complete	The complete_entity tool has been replaced by the unified orgx_act tool.

​Tool Catalog Overview

​Recommended Entry Points

​orgx_decide

​orgx_spawn

​orgx_search read-only

​orgx_decide

​orgx_recommend read-only

​Decisions

​orgx_decide

​get_decision_history read-only

​orgx_decide read-only

​orgx_decide

​Agents

​orgx_spawn read-only

​orgx_spawn

​orgx_recommend read-only

​orgx_spawn

​Memory

​orgx_search read-only

​Initiative Monitoring

​orgx_recommend read-only

​Entity Management

​batch_create_entities

​batch_delete_entities

​comment_on_entity

​orgx_write

​orgx_act

​orgx_inspect read-only

​orgx_search read-only

​list_entity_comments read-only

​scaffold_initiative

​update_entity

​orgx_act dry_run=true read-only

​Organization

​orgx_recommend read-only

​Planning

​orgx_plan

​get_active_sessions read-only

​orgx_plan

​orgx_plan

​orgx_plan

​Scoring & Queue

​get_scoring_signals read-only

​orgx_recommend read-only

​Streams

​get_initiative_stream_state read-only

​update_stream_progress

​Client Integration

​orgx_spawn

​orgx_spawn read-only

​orgx_apply_changeset

​orgx_emit_activity

​record_quality_score

​sync_client_state

​Workspace

​workspace

​Onboarding

​configure_org

​Stats

​stats read-only

​Intelligence Flywheel

​orgx_recommend read-only

​get_my_trust_context read-only

​orgx_recommend read-only

​get_relevant_learnings read-only

​record_outcome

​start_autonomous_session

​submit_learning

​Billing

​account_status read-only

​account_upgrade

​account_usage_report read-only

​Other

​get_decision_detail read-only

​get_job_timeline

​get_logs

​get_run_debug_bundle

​get_session_state

​get_trace

​queue_action

Tool Catalog Overview

Recommended Entry Points

orgx_decide

orgx_spawn

orgx_search `read-only`

orgx_decide

orgx_recommend `read-only`

Decisions

orgx_decide

get_decision_history `read-only`

orgx_decide `read-only`

orgx_decide

Agents

orgx_spawn `read-only`

orgx_spawn

orgx_recommend `read-only`

orgx_spawn

Memory

orgx_search `read-only`

Initiative Monitoring

orgx_recommend `read-only`

Entity Management

batch_create_entities

batch_delete_entities

comment_on_entity

orgx_write

orgx_act

orgx_inspect `read-only`

orgx_search `read-only`

list_entity_comments `read-only`

scaffold_initiative

update_entity

orgx_act dry_run=true `read-only`

Organization

orgx_recommend `read-only`

Planning

orgx_plan

get_active_sessions `read-only`

orgx_plan

orgx_plan

orgx_plan

Scoring & Queue

get_scoring_signals `read-only`

orgx_recommend `read-only`

Streams

get_initiative_stream_state `read-only`

update_stream_progress

Client Integration

orgx_spawn

orgx_spawn `read-only`

orgx_apply_changeset

orgx_emit_activity

record_quality_score

sync_client_state

Workspace

workspace

Onboarding

configure_org

Stats

stats `read-only`

Intelligence Flywheel

orgx_recommend `read-only`

get_my_trust_context `read-only`

orgx_recommend `read-only`

get_relevant_learnings `read-only`

record_outcome

start_autonomous_session

submit_learning

Billing

account_status `read-only`

account_upgrade

account_usage_report `read-only`

Other

get_decision_detail `read-only`

get_job_timeline

get_logs

get_run_debug_bundle

get_session_state

get_trace

queue_action