Mintlify now shows analytics on AI agent traffic to your docs, helping teams understand how agents read, search, and rely on documentation, and how to improve the agent experience with tools like llms.txt, skill.md, content negotiation, and MCP.

AI agents are already reading your documentation. In many cases, they are reading it more often than humans.

Today, Mintlify now shows you exactly how AI agents interact with your docs. You can see which agents have visited, which pages they access most frequently, and what searches they perform through MCP. This data is collected by analyzing incoming user agents and matching them against known AI agent signatures.

AI agents increasingly act as the interface between users and software. They read docs to answer questions, generate code, decide which APIs to call, and determine whether a tool is worth using at all.

Agents do not skim, infer intent generously, or adapt to ambiguity. They depend on clear structure, explicit definitions, and machine-readable signals. If your docs are hard to parse or incomplete, agents may fail silently or choose alternatives.

Mintlify sites support both human readers and AI agents. Features like llms.txt and skill.md provide explicit entry points for agents to understand what your docs contain and how they should be used. Content negotiation ensures agents can retrieve clean, structured representations of your docs, optimized for programmatic consumption while humans still have a beautifully designed experience.

Combined with consistent structure, predictable navigation, and MCP support, Mintlify makes it easier for agents to retrieve the right information and act on it correctly.

With agent analytics, you can now see how well that system is working and iterate with real data.

AI agents are already using your docs, and with the right structure and analytics, you can design that experience instead of guessing at it.

Try it out today and let us know what you think.