> For the complete documentation index, see [llms.txt](https://docs.ox.security/llms.txt). Markdown versions of documentation pages are available by appending `.md` to page URLs; this page is available as [Markdown](https://docs.ox.security/vibesec/agent-ai-bom.md).

# AI Inventory

The Agent AI BOM page provides an inventory of the AI ecosystem surrounding your organization's AI coding agents.

It gives security teams visibility into the components and services used by AI coding agents, such as MCP servers, external SaaS systems, and AI models, helping them understand and govern the organization's AI stack.

OX correlates those events into the entries shown on this page, so you can answer questions such as:

* Which MCP servers is your team using
* Which external SaaS systems are agents reaching into
* Which AI models are the agents running on
* Which developers are calling them
* How often each one is used
* When each was last active

<figure><img src="https://884876233-files.gitbook.io/~/files/v0/b/gitbook-x-prod.appspot.com/o/spaces%2FdK3XMLdV8zRg847RmGmZ%2Fuploads%2Fgit-blob-7aee4de096a7087247eb1fccb37de18bceea228a%2FAgent%20AI%20BOM.png?alt=media" alt="" width="563"><figcaption></figcaption></figure>

From the Agent AI BOM page, you can open the following tabs:

* [**MCP Servers**:](/vibesec/agent-ai-bom/agent-ai-bom-mcp-servers.md) The MCP servers your developers have wired up to their AI coding agents.
* [**External SaaS**:](/vibesec/agent-ai-bom/agent-ai-bom-external-saas.md) Third-party SaaS systems (such as GitHub, GitLab, Jira, Slack, AWS, and Kubernetes) that agents reach into through commands.
* [**AI Models**:](/vibesec/agent-ai-bom/agent-ai-bom-ai-models.md) The AI models powering agent reasoning and code generation.


---

# 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://docs.ox.security/vibesec/agent-ai-bom.md?ask=<question>&goal=<user_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.
