ElevenLabs MCP server for AI agents

The ElevenLabs MCP Server is an official integration that enables AI assistants and development environments to interact with ElevenLabs' powerful Text-to-Speech and audio processing capabilities. It allows applications like Claude Desktop, Cursor, Windsurf, and OpenAI Agents to generate speech, clone voices, transcribe audio, and perform other audio-related tasks.

Installation

Using Claude Desktop

Obtain your API key from ElevenLabs (free tier includes 10k credits per month)

Install uv (Python package manager):

curl -LsSf https://astral.sh/uv/install.sh | sh

Configure Claude Desktop:
- Navigate to Claude > Settings > Developer > Edit Config > claude_desktop_config.json
- Add the following configuration:
```
{
  "mcpServers": {
    "ElevenLabs": {
      "command": "uvx",
      "args": ["elevenlabs-mcp"],
      "env": {
        "ELEVENLABS_API_KEY": "<insert-your-api-key-here>"
      }
    }
  }
}
```
Note for Windows users: Enable "Developer Mode" in Claude Desktop by clicking "Help" in the hamburger menu and selecting "Enable Developer Mode".

Using Other MCP Clients

For clients like Cursor and Windsurf:

Install the package:
```
pip install elevenlabs-mcp
```

Generate the configuration:

python -m elevenlabs_mcp --api-key=YOUR_API_KEY --print

Copy the generated configuration to the appropriate directory specified by your MCP client.

Usage Examples

⚠️ Note: ElevenLabs credits are required to use these tools.

Here are some example prompts you can use with Claude:

"Create an AI agent that speaks like a film noir detective and can answer questions about classic movies"
"Generate three voice variations for a wise, ancient dragon character, then I will choose my favorite voice to add to my voice library"
"Convert this recording of my voice to sound like a medieval knight"
"Create a soundscape of a thunderstorm in a dense jungle with animals reacting to the weather"
"Turn this speech into text, identify different speakers, then convert it back using unique voices for each person"

Advanced Configuration

File Output Settings

Configure file handling using these environment variables:

ELEVENLABS_MCP_BASE_PATH: Base path for file operations (default: ~/Desktop)
ELEVENLABS_MCP_OUTPUT_MODE: Controls how generated files are returned (default: files)

Output Modes

The ELEVENLABS_MCP_OUTPUT_MODE supports three options:

files (default): Saves files to disk and returns file paths

"env": {
  "ELEVENLABS_API_KEY": "your-api-key",
  "ELEVENLABS_MCP_OUTPUT_MODE": "files"
}

resources: Returns files as MCP resources (binary data as base64-encoded, text as UTF-8)

"env": {
  "ELEVENLABS_API_KEY": "your-api-key",
  "ELEVENLABS_MCP_OUTPUT_MODE": "resources"
}

both: Saves files to disk AND returns them as MCP resources

"env": {
  "ELEVENLABS_API_KEY": "your-api-key",
  "ELEVENLABS_MCP_OUTPUT_MODE": "both"
}

Data Residency

Specify the data residency region with:

"env": {
  "ELEVENLABS_API_KEY": "your-api-key",
  "ELEVENLABS_API_RESIDENCY": "us"
}

Note: Data residency is an enterprise-only feature. Default is "us".

Troubleshooting

Server logs can be found at:

Windows: %APPDATA%\Claude\logs\mcp-server-elevenlabs.log
macOS: ~/Library/Logs/Claude/mcp-server-elevenlabs.log

Common Issues

Tool Timeout Errors

Some ElevenLabs operations like voice design can take time to process. Timeout errors may occur in dev mode but shouldn't happen when using Claude Desktop.

"MCP ElevenLabs: spawn uvx ENOENT" Error

If you encounter this error, find the absolute path to uvx:

which uvx

Then update your configuration with the full path:

"command": "/usr/local/bin/uvx"

How to install this MCP server

For Claude Code

To add this MCP server to Claude Code, run this command in your terminal:

claude mcp add-json "ElevenLabs" '{"command":"uvx","args":["elevenlabs-mcp"],"env":{"ELEVENLABS_API_KEY":"<insert-your-api-key-here>"}}'

See the official Claude Code MCP documentation for more details.

For Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > Tools & Integrations and click "New MCP Server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "ElevenLabs": {
            "command": "uvx",
            "args": [
                "elevenlabs-mcp"
            ],
            "env": {
                "ELEVENLABS_API_KEY": "<insert-your-api-key-here>"
            }
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explicitly ask the agent to use the tool by mentioning the tool name and describing what the function does.

For Claude Desktop

To add this MCP server to Claude Desktop:

1. Find your configuration file:

macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
Windows: %APPDATA%\Claude\claude_desktop_config.json
Linux: ~/.config/Claude/claude_desktop_config.json

2. Add this to your configuration file:

{
    "mcpServers": {
        "ElevenLabs": {
            "command": "uvx",
            "args": [
                "elevenlabs-mcp"
            ],
            "env": {
                "ELEVENLABS_API_KEY": "<insert-your-api-key-here>"
            }
        }
    }
}

3. Restart Claude Desktop for the changes to take effect