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

# Concepts

- [The Three Actors](https://www.cakewalk.security/docs/ai-agent-access/concepts/the-three-actors.md): Every Agent action involves three actors: the User who delegates, the Agent acting for them and the Connection accessed. This is the core model of Cakewalk Agent Access.
- [The MCP Gateway](https://www.cakewalk.security/docs/ai-agent-access/concepts/the-mcp-gateway.md): The MCP Gateway is the proxy every Agent tool call passes through. It evaluates Policy, mediates credentials, controls timing and records every decision.
- [The Tool Call Lifecycle](https://www.cakewalk.security/docs/ai-agent-access/concepts/the-tool-call-lifecycle.md): Every Agent tool call follows the same six-step path through the MCP Gateway. This page walks through what happens at each step.
- [Roles and Permissions](https://www.cakewalk.security/docs/ai-agent-access/concepts/roles-and-permissions.md): Cakewalk Agent Access has two roles: Admin and Member. This page defines what each can do.
- [Policies](https://www.cakewalk.security/docs/ai-agent-access/concepts/policies.md): Policies define what Agents are allowed to do, what requires human approval, and what is always blocked. They are the core governance surface in Cakewalk Agent Access.
- [Connection and Agent Statuses](https://www.cakewalk.security/docs/ai-agent-access/concepts/connection-and-agent-statuses.md): Connections and Agents each have their own status taxonomy. This page defines every status and what it means.
- [The Tool Call Record](https://www.cakewalk.security/docs/ai-agent-access/concepts/audit-log.md): Every tool call the MCP Gateway handles leaves a record: who, what, which Policies fired and what was exchanged. This is how Admins answer "why did the Agent do that?"
- [Gateway Trust and Security](https://www.cakewalk.security/docs/ai-agent-access/concepts/trust-and-security.md): Cakewalk Agent Access is built on Credential Mediation and a clear layer boundary. This page covers what Cakewalk protects, how and what stays with the downstream apps.


---

# 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://www.cakewalk.security/docs/ai-agent-access/concepts.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.