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

# Safety & Security

The Dapta MCP is built so you can hand it to an AI client without worrying about surprise changes or cross-account leaks. Three guarantees back that up.

***

## Workspace isolation

Every call is scoped to the workspace tied to your API key. **You cannot read or change another workspace's data.** The MCP resolves your workspace from the key itself, so there is no way to point it at someone else's account by passing a different ID.

***

## Preview, then commit on all writes

No create, update, or execute happens without a preview you can review first. When Claude is about to change something, it shows you exactly what will change and returns a preview token. **Nothing is written until you confirm and a matching commit step runs.**

{% hint style="info" %}
The single exception is creating a brand-new voice agent, which is created directly once you have supplied the details. Every other write goes through preview, then commit.
{% endhint %}

***

## One key per workspace, shown once

Treat the key like a password.

* **One active key per workspace.** Revoke the existing key before minting a new one.
* **Shown once.** Keys are displayed only at mint time. Save yours immediately.
* **Owner-only.** Only workspace owners can mint or revoke keys.
* **Revoke and re-mint** if a key is ever exposed.

<figure><img src="/files/UlYEE8UfDRALpOmNzfjD" alt="The MCP Access page showing an active key with a truncated prefix, an ACTIVE pill, and a Revoke button"><figcaption><p>The active key on the MCP Access page. The full key is never shown again after mint time. Use Revoke to invalidate it.</p></figcaption></figure>

***

## Related

{% content-ref url="/pages/nD2km2sMKwMbq1jr2B87" %}
[Key Concepts](/dapta-mcp/key-concepts.md)
{% endcontent-ref %}

{% content-ref url="/pages/rZHgP7MaYxEYKZWNWWUE" %}
[Mint your API key](/dapta-mcp/setup/mint-your-api-key.md)
{% endcontent-ref %}


---

# 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 dynamically by asking a question.

Perform an HTTP GET request on the current page URL with the `ask` query parameter:

```
GET https://docs.dapta.ai/dapta-mcp/safety-and-security.md?ask=<question>
```

The question should be specific, self-contained, and written in natural language.
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.