> For the complete documentation index, see [llms.txt](https://gitbook.com/docs/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://gitbook.com/docs/analytics/insights/agents-and-mcp.md).
# Agents & MCP
Track how LLMs, coding agents, and crawlers read your documentation
The **Agents & MCP** report covers everything reading your site that isn’t a person: LLMs, coding agents, crawlers, and any tool connected to your site’s [MCP server](/docs/ai-for-your-readers/mcp-servers-for-published-docs.md).
To open it, go to **Analyze → Agents & MCP** in your site’s sidebar.
At the top, you’ll see the pages agents read, their share of everything read on your site, and the number of MCP calls. The **Who reads this site** chart splits reads between people and agents, so you can watch that balance shift over time. See [Site analytics](/docs/analytics/insights.md) for filters, time periods, and comparing periods.
The Agents & MCP report.
## Surfaces
Agents reach your content through several surfaces, and the report counts each one:
* **Markdown**: pages requested as `.md`.
* **llms.txt**: your [LLM-ready](/docs/getting-started/llm-ready-docs.md) index files.
* **MCP**: reads through your site’s MCP server.
* **Site page views** and **RSS**: agents reading your site the way a browser would.
## MCP activity
Three cards cover what tools did with your docs: the **MCP tools** they called, the **MCP search queries** they ran, and the **pages they read through MCP**. Together they show which parts of your documentation your product’s AI integrations depend on.
## Which agents, and what they read
**Agents** ranks the clients reading your site. Pick a surface to see who reads through it. Clients that don’t identify themselves are grouped as **Unidentified**.
**Pages read** ranks your content by how much agents read it, on the surface they read it through.
{% hint style="info" %}
If agents rarely reach your content, see [LLM-ready docs](/docs/getting-started/llm-ready-docs.md) for how to make your site easier for AI tools to discover and read.
{% endhint %}
---
# 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 by asking a question.
Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters:
```
GET https://gitbook.com/docs/analytics/insights/agents-and-mcp.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 `automate deployments from our CI pipeline` 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.
