AppsFlyer Expands Agentic AI and MCP Tools to Empower Marketers with Trusted Automation

AppsFlyer announced a product release to deepen its agentic AI offering. The expanded Agent Hub and new MCP tools let marketing teams investigate and act on their AppsFlyer data through automated workflows with high quality, governed agentic AI infrastructure.

As automation becomes an integral part of everyday workflows, AppsFlyer Agent Hub is establishing the architecture required for AI to run reliably, delivering the capabilities needed to empower marketers through 2027 and beyond. With transparent decision-making accessible in every workflow, teams can understand, evaluate, and trust the reasoning behind every AI recommendation. Marketers will be empowered to strategize based on recommendations from agents, whether that is investigating fraud spikes, spotting creative fatigue, or recommending Apple Ads bid changes.

“Marketing teams are moving from manual campaign orchestration to agentic execution,” said Inna Weiner, VP Product at AppsFlyer. “With this release, AppsFlyer is giving marketers trusted, agentic tools that can analyze, recommend, and act on their data to deliver clear value for growth.”

Marketing Technology News: MarTech Interview with Gil Bouhnick, Director of Product @ AppsFlyer

The new products include:

Agent Hub

• Create an Agent. You can now build your own agent by describing any marketing performance workflow. The agent pulls your data down to the event level, analyzes it, and delivers the insights to your Slack or email on the schedule you set. It can also run root cause analysis and recommend the next action.
• Apple Ads Share of Voice Agent. This is the first AppsFlyer agent that not only recommends – but takes actions (with your approval). It estimates share of voice per keyword and geo, recommends a bid change when you are off target, and executes bid change to Apple Ads directly from AppsFlyer. You retain full control, as updates are only applied upon your approval. In closed beta, available through your CSM.

Marketing Technology News: Campaign Agent Governance: Why Autonomous Marketing Needs Budget and Brand Controls Before Execution

MCP

• Availability of Protect Data via the MCP. You can now access your Protect360 data directly from your own AI tools. For example, you can break down fraud concentration by geo for the last 30 days or find out which custom validation rules drove the most blocks during a specific period.
• Creative Performance Data. Exposes creative-level spend, reach, conversion, retention, and revenue cohorts directly to your AI tool, so teams can identify winning and fatiguing creatives faster, and build automation around it.
• OneLink Link Creation. Turns a plain-language campaign description into a fully configured OneLink. Nothing is created until the marketer approves it.
• Partner Integration settings. Surfaces a partner integration’s configuration, attribution windows, postback rules, and event mappings to any MCP client, so marketers and support teams can diagnose setup issues in conversation.

All MCP capabilities are available in the AI assistant.