Back

Adobe Marketing Agent MCP Server

Connect to the Adobe Marketing Agent MCP server to analyze your Adobe Experience Platform marketing data across organizations, sandboxes, and dataviews using AI agents on Gumloop, Claude, Cursor, or Codex.

MCP server URL

https://adobe-marketing-agent.gumstack.com/mcp

Works with

Tools 12

  • 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.

  • 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.

  • 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.

  • Core Set Dataview

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

  • Core Get Task

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

  • Core List Tasks

    List async tasks for a conversation context_id.

  • 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.

  • 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.

  • 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.

  • Adobe Marketing Agent Mcp Widget

    This MCP server offers a comprehensive suite of capabilities designed to enhance user interaction with Adobe Experience Cloud applications. It enables users to discover and map XDM attributes relevant to their queries, analyze business metrics through visualizations and data tables, and gain insights into product features and best practices. Additionally, it provides statistical analysis of audience sizes and trends, evaluates journey performance and conflicts, and retrieves detailed metadata about various AEP entities, facilitating informed decision-making and operational efficiency.

  • 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").

  • 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.

Frequently asked questions

Related MCP servers

Further reading

What is Adobe Marketing Agent MCP?

The Adobe Marketing Agent MCP server gives AI agents access to your Adobe Experience Platform marketing data through Adobe’s analytical assistant. That means agents can set the organization, sandbox, and dataview they’re working in, ask analytical questions about your Adobe Experience Cloud data, run those requests as async tasks, and track each task to completion. It works across your Adobe orgs, sandboxes, and dataviews so an agent always analyzes the right slice of data.

If your team spends time pulling marketing insights out of Adobe Experience Platform by hand, switching to the right sandboxes, picking the correct dataviews, building and waiting on queries, or copying numbers into a deck, you should consider trying AI agents. Just describe the questions you want answered, and your AI agent will set the context, run the analysis, and return the results for you.

MCP stands for Model Context Protocol. It’s an open standard that gives AI agents a way to connect to external tools and services. Instead of navigating the Adobe Experience Platform interface, managing credentials, and stitching queries together yourself, you connect your Adobe account to Gumloop once. After that, you can analyze your marketing data just by chatting with your AI agent.

What you can do with Adobe Marketing Agent MCP on Gumloop

  • Set your organization, sandbox, and dataview

    Switch the active org, sandbox, and dataview for a session, so an agent always analyzes the exact environment and dataset you mean before it runs anything.

  • Ask analytical questions about your marketing data

    Use Adobe’s marketing analytics assistant to explore your Adobe Experience Cloud data, so an agent can answer questions about performance and audience behavior without you hand-building each query.

  • Run analysis as async tasks

    Kick off analytical requests as tasks and let them run in the background, so longer analyses don’t block the conversation.

  • Track task status and events

    Get the status and new events for a running task and list the tasks in a conversation, so an agent can poll progress and return results the moment they’re ready.

  • Approve or cancel proposed plans

    When the assistant proposes a plan step that needs your call, submit the final decision to complete or cancel it, so you stay in control of what runs against your data.

  • Manage session context and preferences

    Read or clear your persisted org, sandbox, dataview, and region preferences, so repeated analysis picks up where you left off instead of resetting each time.

How to connect the Gumloop Adobe Marketing Agent MCP Server

  1. Create a Gumloop account

    Sign up at gumloop.com. Every new account starts with a 14-day free trial.

  2. Add the Adobe Marketing Agent MCP server

    Copy your MCP server URL from Gumloop and add it to your preferred client (Claude, Cursor, or Gumloop workflows). You'll authorize on first use.

  3. Start using Adobe Marketing Agent in your AI workflows

    That's it. That’s it: your hosted Adobe Marketing Agent MCP server is live, and the same server URL works in any MCP client you’ve added it to. Your AI agent can now set the right context and analyze your Adobe Experience Platform marketing data on request. Use it inside a Gumloop automation, in Claude Desktop, or in Cursor.

Adobe Marketing Agent MCP use cases

  • Self-serve marketing analytics for growth teams

    Instead of filing a request with the analytics team, a marketer can ask a Gumloop agent a question about campaign performance. The agent sets the right sandbox and dataview, runs the analysis, and returns the answer with the numbers, so insights don’t wait on a queue.

  • Weekly performance summaries for marketing leaders

    On a schedule, an agent can run a set of standing analytical questions against the correct dataview, wait for the tasks to finish, and compile the results into a Slack message or Google Sheet, so leaders get a current readout without anyone rebuilding the report.

  • Audience and segment exploration for lifecycle teams

    A lifecycle marketer can ask an agent to explore audience behavior in a specific sandbox, review what the assistant proposes, and approve the analysis to run, keeping a human in the loop while the agent handles the mechanics.

  • Multi-sandbox reporting for enterprise marketing ops

    Teams that run several Adobe sandboxes can have an agent switch between orgs and sandboxes, run the same analysis in each, and assemble a side-by-side view, so ops doesn’t have to manually repeat the same steps per environment.

  • Cross-tool marketing agents

    Combine Adobe Marketing Agent with Slack, Google Sheets, and Notion in a single agent. Run an analysis in Adobe Experience Platform, drop the summary into a shared doc, and notify the channel, so marketing data reaches the rest of your stack.

Why use Gumloop for Adobe Marketing Agent MCP

  • Connect once, no credential wrangling

    Working directly against Adobe Experience Platform usually means managing OAuth credentials, org and sandbox IDs, and API calls in code. With Gumloop you connect your Adobe account once and the connection is handled for you. No config files, token juggling, or coding against the Adobe APIs necessary.

  • Works with multiple MCP clients

    Use the Adobe Marketing Agent MCP server in Claude Desktop, Cursor, Codex, or directly inside Gumloop agents. Same server URL, works with any MCP client.

  • Chain Adobe Marketing Agent with 100+ other integrations

    Combine Adobe Marketing Agent with Slack, Google Sheets, Google Analytics, and other MCP tools in a single AI agent. Run an analysis, process the result, and write it wherever your team works.

  • Enterprise-grade and scalable

    Built for teams, with role-based permissions and dedicated support for Pro users. For details on Gumloop’s security practices, see trust.gumloop.com.

  • Start with a free trial

    You can test the Adobe Marketing Agent MCP integration during Gumloop’s 14-day free trial before committing. Paid plans start at $37/month.