> ## Documentation Index
> Fetch the complete documentation index at: https://www.voiceflow.com/docs/llms.txt
> Use this file to discover all available pages before exploring further.

# Connect coding agent

> Connect Claude Code, Codex or Cursor to Voiceflow with the setup prompt, CLI or MCP server, verify access, and find the tools for your next task.

Work with your Voiceflow projects from the coding agent you already use. Connect through the Voiceflow CLI or MCP server, then ask your agent to inspect projects, build agent behavior or work with your documentation.

## Set up your connection

Connect your assistant to Voiceflow with the setup prompt. It handles your connection, documentation access, and skills where supported. Choose your coding agent or **CLI** for manual connection instructions.

#### Setup prompt

    Paste this prompt into your AI assistant:

    ```text Setup prompt wrap
    Set up Voiceflow by following https://www.voiceflow.com/agents/setup
    ```

    Your assistant will reuse existing connections or set up CLI or MCP access, connect Voiceflow's documentation, and install the Voiceflow skills where your client supports them. Complete browser sign-in when prompted; your assistant will verify the connection before finishing.

#### Claude Code

### 1. Add Voiceflow

        Run this command in your terminal:

        ```bash
        claude mcp add --transport http voiceflow https://mcp.voiceflow.com/mcp
        ```

### 2. Sign in to Voiceflow

        Open Claude Code, run `/mcp`, select **voiceflow**, and choose **Authenticate**. Sign in to Voiceflow in your browser and approve the connection.

        Connecting grants your client access to read and change the projects your account can access. [MCP authentication](/docs/api-reference/authentication#mcp) explains the permissions.

### 3. Confirm the connection

        Ask Claude Code:

        ```text
        List my Voiceflow projects.
        ```

        A project list confirms the connection is working.

#### Codex

### 1. Add Voiceflow

        Run this command in your terminal:

        ```bash
        codex mcp add voiceflow --url https://mcp.voiceflow.com/mcp
        ```

### 2. Sign in to Voiceflow

        If adding the server already completed sign-in, continue to the next step. Otherwise, run:

        ```bash
        codex mcp login voiceflow
        ```

        Sign in to Voiceflow in your browser and approve the connection.

        Connecting grants your client access to read and change the projects your account can access. [MCP authentication](/docs/api-reference/authentication#mcp) explains the permissions.

### 3. Confirm the connection

        Ask Codex:

        ```text
        List my Voiceflow projects.
        ```

        A project list confirms the connection is working.

#### Cursor

### 1. Add Voiceflow

        Add this configuration to `.cursor/mcp.json` in your project, or merge the `voiceflow` entry into your existing `mcpServers`:

        ```json
        {
          "mcpServers": {
            "voiceflow": {
              "url": "https://mcp.voiceflow.com/mcp"
            }
          }
        }
        ```

### 2. Sign in to Voiceflow

        When Cursor prompts you to authenticate, sign in to Voiceflow in your browser and approve the connection.

        Connecting grants your client access to read and change the projects your account can access. [MCP authentication](/docs/api-reference/authentication#mcp) explains the permissions.

### 3. Confirm the connection

        Ask Cursor:

        ```text
        List my Voiceflow projects.
        ```

        A project list confirms the connection is working.

#### CLI

    Run these commands yourself in your local terminal.

### 1. Install the Voiceflow CLI

        On macOS or Linux:

        ```bash
        curl -fsSL https://raw.githubusercontent.com/voiceflow/cli/master/scripts/install.sh | bash
        ```

        On Windows, use PowerShell:

        ```powershell
        iwr -useb https://raw.githubusercontent.com/voiceflow/cli/master/scripts/install.ps1 | iex
        ```

### 2. Sign in to Voiceflow

        ```bash
        vf auth login
        ```

        Follow the sign-in instructions in your terminal.

### 3. Confirm the connection

        ```bash
        vf workspace list --output-format json
        ```

        A workspace list confirms the connection is working. If you use a personal or service key, access depends on that key's permissions; see [CLI authentication](/docs/api-reference/authentication#cli).

## Explore your connected tools

### [Voiceflow MCP server](/docs/mcp/voiceflow)

Find the tools your coding agent can use to read and manage projects, build agents and inspect conversations.

### [Voiceflow CLI](/docs/cli/overview)

Manage projects from your terminal and use CLI commands in scripts and automated workflows.

### [Docs MCP server](/docs/mcp/knowledge)

Give your coding agent read-only documentation search, with no sign-in or access to project data.

### [Platform APIs](/docs/api-reference/api-overview)

Look up requests, parameters and responses for building and managing agents and their resources.
