> For the complete documentation index, see [llms.txt](https://docs.exads.com/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.exads.com/mcp/mcp-server.md). # MCP Server The MCP Server is an optional add-on for your EXADS powered platform. It lets your advertisers and publishers connect AI assistants and tools such as Claude, ChatGPT, Cursor, or any custom agent directly to their account on your platform through the Model Context Protocol (MCP). Once connected, they can ask questions about their performance in plain language and get instant answers without writing any code or building custom integrations. Because EXADS is a white-label platform, the MCP Server runs entirely under your own brand and domain. Your users authorize access against your own admin panel. EXADS is never exposed to the end user, so the experience is fully yours. This feature is turned off by default on all networks. Contact your EXADS representative to enable the MCP Server for your network. The MCP Server is in active development. At the moment it provides **read access to advertiser and publisher statistics, advertiser campaign configurations, and publisher site and zone configurations**. It also lets advertisers create and update their campaigns, and publishers create and update their sites and zones. Each account can query only its own data, and each user chooses what an AI client may do when they connect it. --- # Agent Instructions This documentation is published with GitBook. GitBook is the documentation platform designed so that both humans and AI agents can read, navigate, and reason over technical content effectively. Learn more at gitbook.com. ## Querying This Documentation If you need additional information that is not directly available in this page, you can query the documentation dynamically by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.exads.com/mcp/mcp-server.md?ask=&goal= ``` `ask` is the immediate question: it should be specific, self-contained, and written in natural language. `goal` is what the user is ultimately trying to achieve, the reason they need the answer. Sharing it helps GitBook give you a better, more relevant answer. A goal is most helpful when it describes the outcome the user wants rather than restating the question. For example, with `ask=how do I create an API token`, a goal like `build a script that syncs our docs to a CMS` lets GitBook tailor the answer to that use case. The response will contain a direct answer to the question and relevant excerpts and sources from the documentation. Use this mechanism when the answer is not explicitly present in the current page, you need clarification or additional context, or you want to retrieve related documentation sections.