# Dapta MCP: Overview

The **Dapta MCP** lets you run your Dapta workspace from inside an AI client like **Claude Desktop**, **Claude Cowork**, or **Claude Code**, all in plain language. Instead of clicking through the dashboard, you ask Claude to "create a voice agent," "show me last week's connection rate," or "find my qualified leads," and it does it for you.

It is built on the **Model Context Protocol (MCP)**, an open standard for connecting AI assistants to external systems. You connect once with an API key (a one-click plugin for Claude Desktop and Cowork, or a single command plus the skills bundle for Claude Code), and Claude can then drive your voice and text agents, Flow Studio automations, call analytics, sales-meeting insights, identity and billing, and web research, all from a chat.

{% hint style="info" %}
This is the same intelligence that powers **Dapti**, our in-app assistant. The difference is where it runs: the MCP brings Dapta into the AI client you already use, instead of the chat inside `app.dapta.ai`.
{% endhint %}

***

## What you can do at a glance

| Area                        | Examples                                                          |
| --------------------------- | ----------------------------------------------------------------- |
| **Voice agents**            | Create, configure, and calibrate agents; analyze call performance |
| **Text & WhatsApp agents**  | Build chat agents, connect WhatsApp, refine prompts               |
| **Flow Studio automations** | Design, validate, and run automation flows                        |
| **Call & lead analytics**   | Call stats, connection rates, qualified-lead extraction           |
| **Sales meetings**          | Pull meeting transcripts, action items, and sales tips            |
| **Identity & billing**      | Accounts, users, workspaces, usage, balance, subscription         |
| **Support**                 | Search support history, open tracked tickets                      |
| **Research & docs**         | Research a company from a URL, search Dapta documentation         |

***

## Two building blocks: Tools and Skills

The Dapta MCP gives Claude two things:

* **Tools** are the actions Claude can take: read data, create agents, update prompts, run flows. Think of these as the "hands."
* **Skills** are packaged know-how that teaches Claude *how* and *when* to use those tools correctly for a given task. Think of these as the "playbooks."

You do not need to know any tool names. You describe what you want in plain language, the matching skill activates automatically, and it chooses the right tools for you. The current bundle ships **33 skills** and **128 tools** across 13 domains.

***

## Who this is for

Anyone with access to a Dapta workspace who wants to work faster from an AI client. **Minting an API key requires workspace-owner access.** If you are not an owner, ask your workspace owner for a key, then follow the setup steps below.

***

## Start here

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

{% content-ref url="/pages/MAXWVsEp5drMKkYRSLZw" %}
[Setup & Connection](/dapta-mcp/setup.md)
{% endcontent-ref %}

{% content-ref url="/pages/lwhNZ1XQgGk0Xsk0zZch" %}
[Skills Catalog](/dapta-mcp/skills.md)
{% endcontent-ref %}


---

# Agent Instructions: 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/mcp.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.