Work With Adform MCP Server

Solveiga
Solveiga
  • Updated

Adform MCP Server gives your AI application access to Adform FLOW data and capabilities. The results you receive also depend on your prompts, the skills you use, and how your AI application interprets the data retrieved through MCP. Adform MCP Server can retrieve recommendations, forecasts, and other insights available in Adform FLOW. Any additional analysis, conclusions, or suggestions are generated by your AI application.

Note

Adform does not provide or manage third-party AI applications. You are responsible for any costs charged by your AI application provider, including subscription fees and token consumption.

Important

Your use of Adform MCP Server is subject to your existing agreement with Adform and the MCP Access Notice. MCP provides read-only access and does not extend your existing Adform Platform access rights. You are responsible for ensuring that you are authorized to access and use Adform data through MCP and your chosen AI application, and for reviewing and validating AI-generated outputs before relying on them.

For terms, responsibilities, and restrictions, read the MCP Access Notice.

To explore how to use the Adform MCP Server effectively, see the Adform Academy course Unlock Agentic Potential with Adform MCP Server.

Use Natural Language Prompts

After you connect your AI application to Adform MCP Server, you can use natural-language prompts to access information available in Adform FLOW. You can explore your data, ask questions, review performance and setup, retrieve information, and complete a range of Adform-related tasks directly from your AI application. You can write your own prompts, tailoring them to your specific goals and needs. For example:

  • Give me a branding report for the last 30 days and let me choose the advertiser.

  • Show me underdelivering campaigns for the last 30 days and let me choose the advertiser.

  • Give me a weekly overview of my active campaigns in a table, with a link to each one.

  • Run a delivery health check and identify any blockers. Let me choose the advertiser.

  • For a €10k Display + Native budget in July targeting Germany, what impressions and CTR can I expect?

  • Which domains have high bid volume but low win rate? Show me where we're losing the most auctions. Display the trend in a chart.

  • Which PMP deals have zero or near-zero impressions this week, and what's the likely cause?

  • Show me video completion rate, video starts and average play time by date for the last 30 days. Let me choose the advertiser.

  • Run a tag audit and flag any pending approvals or rejections. Let me choose the advertiser.

  • Show me bid reason analysis — break down why we're losing auctions by reason category and tell me which issues a CPM increase will fix.

  • Find campaigns past their end date that are still active, and line items with no parent order.

Note

To make sure your AI application interprets Adform data correctly, ask for evidence in your prompt. We also recommend that you verify key information against data available on the Adform platform.

Tip

To explore how to use the Adform MCP Server effectively, see the Adform Academy course Unlock Agentic Potential with Adform MCP Server.

Use MCP Skills

Skills are reusable instructions that help AI applications consistently perform specific tasks by following clearly defined workflows. To help you get started, Adform provides a repository that contains prebuilt skills for common Adform workflows, such as campaign performance analysis, delivery monitoring, reporting, and campaign setup reviews. After importing the relevant skills into your AI application, you can use them with the Adform MCP Server to help guide your tasks.

For Adform MCP Server skills and use instructions, see Adform MCP Agentic Skills Repository. Adform provides separate skill packages for Claude and other AI applications because they use skills differently:

  • For Claude, you can import the Claude folder from the Adform Agentic Skills repository as a plugin to conveniently access and use all provided skills. The skills in the Generic folder also work with Claude.

  • For ChatGPT, Copilot, Mistral, and other compatible AI applications, use the skills in the Generic folder.

You can also create your own skills for workflows specific to your needs. For information on creating, adding, and using skills with your AI application, refer to your AI provider's official documentation: ChatGPT, Claude, Copilot, Mistral, or other providers.

Note

Skills help guide AI applications by providing task-specific context and instructions. However, skills don't guarantee a particular outcome, as it still depends on the prompt, the data retrieved through MCP, and how the AI application interprets and applies the skill instructions. Make sure to review and verify the AI-generated responses before use.

Was this article helpful?

/
How can we make it better?

Thank you for your feedback!