Agent directory ยท By company

Microsoft's AI agents and crawlers

Microsoft runs one agent that visit websites: 1 AI and search crawler. Here's what each one does, and how to let them in or keep them out.

Indexes pages so a search engine or AI search tool can find, cite and link to them. Allow it, unless you deliberately want to stay out of that search engine. Blocking it removes you from its results and answers.

  • Bingbot: Microsoft's crawler for Bing. Bing's index powers Microsoft Copilot and many other AI search tools.

Robots.txt for every Microsoft agent

To block every Microsoft agent that reads robots.txt. This also keeps out the ones acting for your customers and the ones that send you visitors, so think twice:

User-agent: bingbot
Disallow: /

Robots.txt is a request, not a lock, and some agents that act for a person in real time may not read it. A decision guide for blocking or allowing AI crawlers.

How to tell if it's really Microsoft

Microsoft publishes ways to check that a request really came from it:

Requests that use Microsoft's names but fail these checks are impostors. Ghost Agent Lab checks every request this way. How to verify AI crawlers.

Which Microsoft agents visit your site? Ghost Agent Lab reads your CDN or server logs and shows every request from them: what they read, what your site sent back, and whether each one was genuine. See agent traffic, or check whether AI agents can use your site for free.