---
canonical_url: "https://docs.composio.dev/toolkits/adobe_marketing_agent_mcp"
markdown_url: "https://docs.composio.dev/toolkits/adobe_marketing_agent_mcp.md"
product: "platform"
version: null
last_updated: null
---

# Adobe Marketing Agent MCP

Adobe Marketing Agent MCP provides authorized Adobe marketing context, preferences, and agent capabilities through Adobe's hosted MCP service.

- **Category:** model context protocol
- **Auth:** DCR_OAUTH
- **Composio-managed OAuth available?** No
- **Tools:** 12
- **Triggers:** 0
- **Slug:** `ADOBE_MARKETING_AGENT_MCP`
- **Version:** 20260910_00

## Tools

### Adobe-marketing-agent-mcp-widget

**Slug:** `ADOBE_MARKETING_AGENT_MCP_ADOBE_MARKETING_AGENT_MCP_WIDGET`

This MCP server offers a comprehensive suite of capabilities designed to enhance user experience with Adobe Experience Platform and related applications. It enables users to analyze audience and segment sizes over time, investigate historical trends and anomalies, and retrieve detailed product knowledge and best practices. Additionally, it facilitates the discovery of relevant XDM fields, provides operational insights into various AEP entities, and supports journey performance analysis, all while generating visualizations and data tables for business metrics, thereby streamlining data-driven decision-making processes.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `async` | boolean | No | Compatibility flag. true implies async execution. |
| `query` | string | Yes | The query or request |
| `chat_id` | string | No | Optional chat/context correlation identifier. |
| `long_running` | boolean | No | Compatibility flag. true implies async execution. |
| `execution_mode` | string ("sync" | "async") | No | Optional execution mode. Use 'async' for polling-based long-running tasks. |

### Core-context-management-widget

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_CONTEXT_MANAGEMENT_WIDGET`


        Interactive widget to view and manage user context. Use this to display current
        organization, sandbox, and dataview, and to allow the user to switch between them.
        Call this widget when the user wants to see their context, list available sandboxes,
        list available dataviews, list available organizations, change sandbox,
        change dataview, or switch organization.
        Note: Users refer to sandboxes by title (e.g. "Production"), not by name (e.g. "prod").
    

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | No | Optional query parameter |

### Core-feedback-widget

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_FEEDBACK_WIDGET`


        Call this widget when the user wants to provide feedback or rate their experience.

        This displays an interactive feedback form with thumbs up/down buttons and rating categories.
        Users can select sentiment (like/dislike) and provide additional comments.

        If widgets are not supported by the surface, the system will automatically fall back
        to text-based feedback using core-provide_feedback tool.
    

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | No | Optional query parameter |

### Core-get task

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_GET_TASK`

Get task status and events for an async task. Use cursor to get only new events since last poll.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `cursor` | integer | No | Return only events with cursor > this value. Default 0 (all events). |
| `task_id` | string | Yes | Task ID to fetch. |

### Core-list tasks

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_LIST_TASKS`

List async tasks for a conversation context_id.

### Core-plan completion decision

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_PLAN_COMPLETION_DECISION`

Submit the user's final decision to complete or cancel a pending plan.

Use this tool when the system has proposed a plan step that requires user confirmation before it can be executed — such as creating an audience, a journey, a campaign, or any other entity. This is the final step that completes the plan.

ALWAYS use this tool when:
- The system is waiting for the user's decision to proceed with a plan
- The user provides an explicit approve or reject response to a pending proposal
- User says "approve", "go ahead", "create it", "looks good", "confirm", "do it"
- User says "reject", "cancel", "don't create it", "decline", "stop"

Parameters:
- decision (required): "approve" to confirm and execute the plan, "reject" to cancel it

Returns the final orchestrator response confirming the plan was completed or cancelled.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `decision` | string ("Approve" | "Reject") | Yes | 'Approve' to accept the mutation proposal, 'Reject' to decline it. |

### Core-provide feedback

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_PROVIDE_FEEDBACK`

Submit user feedback about their experience with the AI assistant.

Accepts a query parameter with the user's feedback message. Automatically classifies sentiment and submits to the feedback API. Use core-feedback-widget instead if the user wants to see a feedback form.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `query` | string | No | The user's feedback message (text mode). Use this for text-based feedback. |
| `comment` | string | No | Additional comment from widget (widget mode) |
| `flagged` | boolean | No | True if the feedback contains or reports harmful content (triggers flag API), False for normal sentiment feedback |
| `pickList` | array | No | Selected feedback options from widget (widget mode) |
| `sentiment` | string ("like" | "dislike") | No | User sentiment from widget (widget mode): 'like' (thumbs up) or 'dislike' (thumbs down) |
| `flagCategories` | array | No | Specific harmful content categories when flagged=true |

### Core-set dataview

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_SET_DATAVIEW`

Set the current dataview context. Use this when the user wants to switch to a different dataview.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `dataviewName` | string | Yes | Name of the dataview to set as current context |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `message` | string | No | Human-readable message about the action |
| `response` | array | No | List of result messages indicating what context was updated |

### Core-set sandbox

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_SET_SANDBOX`

Set the current sandbox context. Use this when the user wants to switch to a different sandbox. The response contains the displayValue (e.g., 'Prod - Production (VA7)') which should be used when talking to the user.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `sandboxName` | string | Yes | Name (technical identifier) of the sandbox to set as current context |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `message` | string | No | Human-readable message about the action |
| `response` | array | No | List of result messages. Contains the sandbox displayValue (e.g., 'Sandbox set to: Prod - Production (VA7)'). Use this displayValue when communicating with the user. |

### Core-switch org

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_SWITCH_ORG`

Switch to a different organization by exchanging the current token. Provide the organization name or IMS Org ID. Use list_orgs to see available organizations first.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `org_name` | string | Yes | Name or IMS Org ID of the organization to switch to (e.g., 'aem62be1' or 'CJM Stage') |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `org_id` | string | No | IMS Organization ID |
| `message` | string | No | Success or error message |
| `org_name` | string | No | Organization name |
| `dataview_id` | string | No | ID of the default dataview set for the new organization |
| `sandbox_name` | string | No | Name of the default sandbox set for the new organization |
| `dataview_name` | string | No | Name of the default dataview set for the new organization |

### Core-switch sandbox dataview

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_SWITCH_SANDBOX_DATAVIEW`

This core system tool updates the current sandbox and/or dataview context for the session.

Parameters:
- sandboxName (optional): Name of the sandbox to set as current context it's usually one word
- dataviewName (optional): Name of the dataview to set as current context

The tool will:
1. Fetch the ID for each provided name from Adobe APIs
2. Update the session store with the IDs
3. Return confirmation of what was updated

Note: At least one parameter must be provided based on what you want to change (sandbox/dataview). Use list_dataviews or list_sandboxes to see available options first.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `sandboxName` | string | No | Name of the sandbox to set as current context (usually one word) required if we want to change to a different sandbox |
| `dataviewName` | string | No | Name of the dataview to set as current context required if we want to change the dataview |

#### Output

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `message` | string | No | Human-readable message about the action |
| `response` | array | No | List of result messages indicating what context was updated |

### Core-user preferences

**Slug:** `ADOBE_MARKETING_AGENT_MCP_CORE_USER_PREFERENCES`

Read or clear the current user's persisted preferences (sandbox, dataview, org, region).

Preferences persist for 90 days across sessions and surfaces. Set automatically when the user configures a sandbox or dataview.

Parameters:
- action (optional): "get" (default) to read, "clear" to delete

Returns JSON with sandbox_name, sandbox_id, dataview_id, dataview_name, org_id, region, updated_at. Fields are null when not set.

#### Input Parameters

| Parameter | Type | Required | Description |
|-----------|------|----------|-------------|
| `action` | string ("get" | "clear") | No | 'get' (default) returns the user's saved preferences. 'clear' deletes all saved preferences. |