> 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/claude-connectors-directory.md). # Connect from the Claude connectors directory Connect Dapta to Claude from the Claude connectors directory: requirements, how to sign in, how to choose a workspace, three prompts to start with, and how your data is protected. **Dapta** is the official Dapta connector for Claude. It lets you operate your Dapta workspace in plain language: voice agents, text and WhatsApp agents, automations, call analytics and more. *** ## What you can do | Area | Examples | | ------------------------------ | ---------------------------------------------------------------------------------------------- | | **Voice agents and analytics** | Create and configure agents. Call stats, connection rates, best hours to dial, qualified leads | | **Voice sequences** | Read and adjust outbound calling lists, contacts and retry rules | | **Text and WhatsApp agents** | Build chat agents, test them, manage versions, connect a WhatsApp line | | **Flow Studio** | Design, validate, create, patch and run automation flows. Read execution logs | | **Dapta databases** | Create databases and tables, read and write the rows automations keep | | **Sales meetings** | Meeting transcripts, action items and statistics | | **Workspace and account** | Phone numbers, knowledge bases, WhatsApp templates, balance, subscription | | **Documentation** | Search Dapta's documentation from the chat | *** ## Requirements A **Dapta account** that is an owner or admin of at least one workspace. The connector works on your own Dapta data, so without an account there is nothing to see. *** ## Connect ### From the directory Once Dapta is listed in the directory: 1. In Claude, open **Connectors**. 2. Find **Dapta** and click **Connect**. 3. Sign in with your Dapta account. 4. Approve the access. ### As a custom connector 1. In claude.ai, Claude Desktop or Cowork, click **+** in the chat box, then **Connectors**, **Add connector** and **Add custom connector**. 2. Name it **Dapta** and paste the server URL: ``` https://mcp.dapta.ai/mcp ``` 3. Leave the advanced settings empty and click **Add**. Claude sends you to Dapta's sign-in page. Enter your Dapta email and the 6-digit code we email you. ### In Claude Code Claude Code uses the connectors of your Claude account: once Dapta is connected in Claude, run `/mcp` and it shows up under the claude.ai connectors. Without a Claude account, add it with one command: {% code title="terminal" overflow="wrap" %} ```bash claude mcp add --transport http --scope user dapta https://mcp.dapta.ai/mcp ``` {% endcode %} Then run `/mcp` inside Claude Code, choose **dapta** and then **Authenticate**. *** ## Choose your workspace If your account has one workspace, Claude uses it. If it has several, Claude lists them by name and asks which one to work in. Answer with the name. * Say **"Switch to \"** to change workspace at any time. * Every answer starts with the workspace it ran in, so you always know where you are. *** ## Three prompts to start with | Prompt | What Claude does | | -------------------------------------------------------------------------------------------------- | ----------------------------------------------------------------------------------------------------------------- | | **"Who am I in Dapta, and which workspaces can I use?"** | Confirms your connection and lists your workspaces, using `whoami` and `list_my_workspaces` | | **"List my voice agents and show me how the newest one is configured."** | Reads your agents and opens the most recent one, using `list_agents` and `get_agent` | | **"Show me the recent runs of my most recently updated flow, and tell me if any of them failed."** | Finds your latest automation and reads its recent runs, using `get_workspace_flows` and `get_flow_execution_logs` | All three only read data. Nothing in your workspace changes. *** ## What Claude can change, and how you are protected Updates, deletions, publishing and flow runs are shown to you as a preview first, and nothing is applied until you confirm. Each tool declares whether it only reads, adds data, or changes and removes existing data, so Claude knows when to ask before acting. Your Dapta API key, your login session and your agents' secret keys are never returned to Claude. {% content-ref url="/pages/7Nwd3yZ8uoxBnjaqiVC6" %} [Safety & Security](/dapta-mcp/safety-and-security.md) {% endcontent-ref %} *** ## When to use an API key instead Signing in is the best option for people. Use an API key for: * **Automations:** custom scripts and scheduled jobs. * **Clients that cannot sign in.** * **A fixed workspace:** a key always works in the one workspace it was created for. {% content-ref url="/pages/zhvtvDJJrqsIADXWzT7U" %} [Mint your API key](/dapta-mcp/setup/mint-your-api-key.md) {% endcontent-ref %} *** ## Privacy and support * **Privacy:** [Privacy and data handling](/dapta-mcp/privacy.md) for this connector, and the [Dapta Privacy Policy](https://dapta.ai/privacy-policy) * **Support:** * **Security reports:** You can revoke the connector's access at any time from your Dapta account settings, or by removing the connector in Claude. *** ## Quick troubleshooting | Symptom | Likely cause | Fix | | ------------------------------------------------- | ------------------------------------------------ | ---------------------------------------------------------------------------------- | | Claude asks which workspace to use | Your account has several workspaces | Answer with the workspace name, not an id. Say "switch to \" to change later | | "workspace is required" in a tool answer | The conversation has not named its workspace yet | Tell Claude the workspace. It repeats the call | | Login page loops, or the connector shows an error | Stale connector session | Remove the Dapta connector and add it again with `https://mcp.dapta.ai/mcp` | {% content-ref url="/pages/S7un1aQruLZ3Ww28VDY8" %} [Troubleshooting](/dapta-mcp/troubleshooting.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 by asking a question. Perform an HTTP GET request on the following URL with the `ask` and `goal` query parameters: ``` GET https://docs.dapta.ai/dapta-mcp/claude-connectors-directory.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.