> ## Documentation Index
> Fetch the complete documentation index at: https://docs.useorgx.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# ChatGPT Integration

> Give ChatGPT organizational memory and human approval workflows through OrgX MCP.

OrgX connects to ChatGPT through the OpenAI Apps SDK using the OrgX MCP server.
Use it when ChatGPT needs durable team memory, decision approvals, artifact
recall, agent delegation, or project execution status.

<Info>
  As of April 27, 2026, ChatGPT support depends on whether your ChatGPT plan and workspace expose
  remote MCP connectors / Developer Mode. If that option is unavailable in your
  account, use Cursor, Claude, VS Code, or the OpenClaw plugin instead.
</Info>

## Questions This Page Answers

* How do I use ChatGPT as a control surface for OrgX, not just a chatbot?
* Which tools should I call for approvals, blockers, and new work dispatch?
* What exact agent IDs should I use when spawning specialist tasks?

## Features

<CardGroup cols={2}>
  <Card title="Approve Decisions" icon="check">
    Review and approve pending decisions with rich widget UI.
  </Card>

  <Card title="Agent Status" icon="robot">
    See what your agents are working on in real-time.
  </Card>

  <Card title="Org Memory" icon="brain">
    Search your knowledge graph for context and history.
  </Card>

  <Card title="Spawn Tasks" icon="play">
    Assign new work to specialist agents.
  </Card>
</CardGroup>

## Getting Started

<Steps>
  <Step title="Enable Developer Mode">
    1. Open ChatGPT **Settings -> Apps & Connectors**
    2. Turn **Developer Mode** on
  </Step>

  <Step title="Add the OrgX Connector">
    1. In **Apps & Connectors**, click **Add Connector** (or **Add MCP Server**)
    2. Enter the MCP endpoint: `https://mcp.useorgx.com/mcp`
    3. Save -- OrgX will
       appear in your connectors list
  </Step>

  <Step title="Authenticate">
    On first use, ChatGPT will prompt you to connect your OrgX account:

    1. Click the authentication link
    2. Sign in to OrgX (creates account if needed)
    3. Grant ChatGPT permission to access your workspace

    <Info>
      OrgX uses OAuth 2.1 for secure authentication. Your credentials are never
      stored by ChatGPT.
    </Info>
  </Step>

  <Step title="Start Using">
    Once connected, just talk to ChatGPT naturally:

    * *"Show me pending decisions"*
    * *"What are my agents working on?"*
    * *"Approve the marketing campaign decision"*
    * *"Search for our pricing strategy decisions"*
    * *"Remember this decision for the team: we are moving onboarding analytics to PostHog."*
  </Step>
</Steps>

## Available Commands

### Tier-0 Intent Tools

Start with these wrapper tools. They map to the natural phrases ChatGPT users
actually type while preserving the underlying OrgX behavior.

| User intent               | Preferred tool   | Underlying OrgX action                                                |
| ------------------------- | ---------------- | --------------------------------------------------------------------- |
| Remember a team decision  | `orgx_decide`    | Records a decision in organizational memory                           |
| Recall prior context      | `orgx_search`    | Searches decisions, artifacts, initiatives, and project context       |
| Review blocked agent work | `orgx_decide`    | Lists pending approvals, then approves or rejects after confirmation  |
| Hand work to an agent     | `orgx_spawn`     | Assigns work to a specialist OrgX agent                               |
| Check project progress    | `orgx_recommend` | Returns initiative health, blockers, milestones, owners, and activity |

### Decision Management

<AccordionGroup>
  <Accordion title="Get Pending Decisions" icon="list">
    **What it does**: Retrieves all decisions waiting for your approval.

    **Example prompts**:

    * "Show my pending decisions"
    * "What needs my approval?"
    * "Any critical decisions waiting?"

    **Parameters**:

    * `limit` (optional): Maximum number to return
    * `urgency_filter` (optional): `all`, `critical`, or `high`
    * `initiative_id` (optional): Filter by specific initiative

    **Response**: Rich widget showing decision cards with approve/reject buttons.
  </Accordion>

  <Accordion title="Approve Decision" icon="check">
    **What it does**: Approves a pending decision and triggers agent execution.

    **Example prompts**:

    * "Approve the homepage redesign decision"
    * "Approve decision D-123 with note: looks good"

    **Parameters**:

    * `decision_id` (required): ID of the decision
    * `note` (optional): Comment to attach

    **Response**: Confirmation widget showing approval status.
  </Accordion>

  <Accordion title="Reject Decision" icon="xmark">
    **What it does**: Rejects a decision with feedback for the agent.

    **Example prompts**:

    * "Reject the email campaign, needs more personalization"
    * "Reject D-456 because budget is too high"

    **Parameters**:

    * `decision_id` (required): ID of the decision
    * `reason` (required): Why you're rejecting

    **Response**: Confirmation widget. Agent receives feedback and may revise.
  </Accordion>

  <Accordion title="Get Decision History" icon="clock-rotate-left">
    **What it does**: Retrieves past decisions on a topic.

    **Example prompts**:

    * "What decisions have we made about pricing?"
    * "Show me past marketing decisions"

    **Parameters**:

    * `topic` (required): What to search for
    * `initiative_id` (optional): Filter by initiative
    * `limit` (optional): Maximum results
  </Accordion>
</AccordionGroup>

### Agent Management

<AccordionGroup>
  <Accordion title="Get Agent Status" icon="robot">
    **What it does**: Shows current agent activity and status.

    **Example prompts**:

    * "What are my agents doing?"
    * "Show me active agents"
    * "Is the engineering agent working on anything?"

    **Parameters**:

    * `agent_id` (optional): Filter to specific agent
    * `include_idle` (optional): Show idle agents too

    **Response**: Widget showing agent cards with current tasks.
  </Accordion>

  <Accordion title="Spawn Agent Task" icon="play">
    **What it does**: Assigns a new task to a specialist agent.

    **Example prompts**:

    * "Have the product agent analyze our competitor positioning"
    * "Ask the marketing agent to draft a blog post about our new feature"

    **Parameters**:

    * `agent` (required): Canonical agent ID (`engineering-agent`, `product-agent`, `marketing-agent`, `sales-agent`, `design-agent`, `operations-agent`, `orchestrator-agent`)
    * `task` (required): What to do
    * `context` (optional): Additional background
    * `initiative_id` (optional): Link to an initiative

    **Response**: Confirmation that task was created and assigned.

    <Warning>
      This requires write permissions. Make sure you've granted agent write
      scopes during authentication.
    </Warning>
  </Accordion>
</AccordionGroup>

### Memory & Search

<AccordionGroup>
  <Accordion title="Query Org Memory" icon="brain">
    **What it does**: Searches your organizational knowledge graph.

    **Example prompts**:

    * "What do we know about enterprise pricing?"
    * "Find artifacts related to the Q1 launch"
    * "Search for previous security audits"

    **Parameters**:

    * `query` (required): What to search for
    * `scope` (optional): `all`, `artifacts`, `decisions`, or `initiatives`
    * `limit` (optional): Maximum results

    **Response**: Widget showing relevant items with excerpts and links.
  </Accordion>

  <Accordion title="Get Initiative Pulse" icon="heart-pulse">
    **What it does**: Shows health and progress of an initiative.

    **Example prompts**:

    * "How is the product launch initiative doing?"
    * "Show me the pulse for initiative I-789"

    **Parameters**:

    * `initiative_id` (required): Which initiative to check

    **Response**: Widget with health score, milestones, blockers, and recent activity.
  </Accordion>
</AccordionGroup>

## Widgets

OrgX uses rich **widgets** to display information in ChatGPT, not just plain text:

<CardGroup cols={2}>
  <Card title="Decisions Widget" icon="list-check">
    Interactive cards with approve/reject buttons, context, and evidence links.
  </Card>

  <Card title="Agent Status Widget" icon="robot">
    Visual cards showing each agent's current task, progress, and health.
  </Card>

  <Card title="Search Results Widget" icon="magnifying-glass">
    Organized results with type icons, excerpts, and deep links.
  </Card>

  <Card title="Initiative Pulse Widget" icon="chart-line">
    Dashboard view with health score, milestone progress, and activity feed.
  </Card>
</CardGroup>

## Permissions & Security

### Scopes

When you authenticate, you can grant different permission levels:

| Scope              | What It Allows                  |
| ------------------ | ------------------------------- |
| `decisions:read`   | View pending and past decisions |
| `decisions:write`  | Approve or reject decisions     |
| `agents:read`      | View agent status and activity  |
| `agents:write`     | Spawn new agent tasks           |
| `initiatives:read` | View initiative details         |
| `memory:read`      | Search organizational knowledge |

<Info>
  The authenticated ChatGPT connector uses `https://mcp.useorgx.com/mcp` and
  requires OrgX OAuth. For no-auth exploration, use the discovery-only public
  endpoint at `https://mcp.useorgx.com/public`; it returns examples and
  connection help, not workspace data.
</Info>

### Data Privacy

* Your messages in ChatGPT are processed by OpenAI per their policies
* OrgX only receives the specific tool calls, not your full conversation
* All API calls are authenticated and scoped to your workspace
* We never store your ChatGPT conversation history

## Troubleshooting

<AccordionGroup>
  <Accordion title="App not appearing in ChatGPT">
    During the current preview, connectors are private and only appear after you
    add them in Developer Mode.

    1. Verify **Settings -> Apps & Connectors -> Developer Mode** is enabled
    2. Confirm you've added `https://mcp.useorgx.com/mcp` as a connector
    3. Restart ChatGPT if the list doesn't refresh
  </Accordion>

  <Accordion title="Authentication failing">
    1. Try clearing your browser cache and re-authenticating 2. Make sure you're
       signing into the correct OrgX workspace 3. Check that your OrgX account is in
       good standing
  </Accordion>

  <Accordion title="Decisions not loading">
    * Ensure you have pending decisions in your OrgX workspace - Check that you've
      granted `decisions:read` permission - Try refreshing by asking "Show pending
      decisions" again
  </Accordion>

  <Accordion title="Can't approve/reject decisions">
    Write operations require the `decisions:write` scope. Re-authenticate and
    make sure to grant write permissions.
  </Accordion>
</AccordionGroup>

## Next Steps

<CardGroup cols={2}>
  <Card title="MCP Client Setup" icon="code" href="/docs/guides/cursor-mcp-setup">
    Connect OrgX from Cursor, Claude, VS Code, and other MCP clients.
  </Card>

  <Card title="MCP Tools Reference" icon="server" href="/docs/api/mcp-tools">
    Full API documentation for all tools.
  </Card>
</CardGroup>