Your agent can reason about marketing. It still needs account tools.
You can build an agent that explains campaign performance in a prototype. Making that agent useful inside a marketing team introduces a different set of tasks: account authorization, data access, execution status, repeated operations, and a record of changes.
Those tasks can consume the work you intended to spend on the agent itself. A prompt cannot supply an account permission boundary or tell you whether an asynchronous launch completed. Your integration needs an operating layer around the model.
Use Superlaunch as the account-facing layer
Connect your OAuth-compatible MCP client to Superlaunch and build the agent’s workflow around the available tools. Superlaunch supplies account access checks, synced Insights, launch operations, rules, context, and Activity. You keep ownership of the model, orchestration, review policy, and evaluation.
Build an internal acquisition assistant
Your team wants an assistant that reviews acquisition performance, proposes a creative launch, and prepares rules for a marketer to review. You run the agent in your own environment and connect it to the team’s authorized accounts.
The following is an illustrative workflow you can adapt to your account.
How the workflow works in practice
Connect through MCP and OAuth
Use an MCP client that supports Superlaunch’s OAuth flow. Connect to https://mcp.superlaunch.pro/mcp and authorize the connection. Select read or write access appropriate to the workflow, within the user’s account and function permissions.
Test the connection with a read-only task before you enable writes. Use an account and function scope that fits the task. An OAuth write scope does not override account permissions, so your agent must handle a denied operation as a real outcome rather than trying a different account.
Discover the tools and available data
Read capabilities before querying Insights. Specify the date range, metrics, conversion event, and attribution settings. Retrieve the relevant brand or account context, and handle pagination and missing data in your agent.
Build the query from Superlaunch’s supported capabilities, then check the selected account’s returned data and coverage. A supported conversion metric does not mean that account has recorded that event. Preserve the reporting period and attribution settings in the result you show the marketer, so they can reproduce the comparison.
Preview, submit, and check the outcome
Set the account’s Launcher campaign and budget limits before the first launch preview. Use Launcher tools to work with creative collections and templates. Show the launch preview for review, submit the approved launch, and poll its status. Treat accepted work as pending until you have its execution result.
Model a launch as work with a lifecycle. A preview can reveal missing configuration; a submitted operation can still be pending or fail during execution. Keep the returned identifiers, check the status, and show the marketer the actual outcome before describing the launch as complete.
Separate recurring execution from agent orchestration
Create native Launcher schedules or autorules for supported recurring account work. Run report generation and other agent orchestration in your own scheduler. Use Activity and run results to investigate denied, failed, or completed actions.
Choose the scheduler that owns the work. A native rule or Launcher schedule can execute supported account operations without the agent session staying open. A weekly narrative report still needs your agent system to start the run, query the data, compose the report, and deliver it through your chosen channel.
Start the conversation with your agent
Adapt this example to your account and the task you want to review.
Read the account’s available Insights metrics and our saved context. Propose a launch and explain the data behind it. Show a preview before any write. After approval, submit once, check the execution result, and report any failed items.
Before you rely on the result
Superlaunch provides the account tools and execution controls. You host and operate your agent, manage its review flow, and handle retries and errors. Both OAuth scopes and current account permissions matter; write scope alone does not grant access to every account.
A useful first step
A useful first integration reads one account, produces a recommendation with evidence, and prepares a launch preview. Add submission only after you can handle permissions, missing configuration, pending work, and failures.
Your developers can focus on agent behavior while reusing Superlaunch’s account tools, recurring execution, permissions, and activity records.
Read the setup documentation