1. Home
  2. Servers
  3. AI Models & Agents
  4. ElevenLabs MCP

Server profile

ElevenLabs MCP

ElevenLabs MCP brings the vendor's speech and audio services into assistant workflows. This official integration supports voice work and transcription, with outputs delivered as files, MCP resources, or both.

View repositoryInstall & configure

Server facts

ElevenLabs MCP

Tech

Runtime / language
pythonPython
Transports
stdio
Remote available
No
Authentication
Not specified

Activity

GitHub stars
1,535Archived on GitHub
Last commit
Data as of

Tags

  • Audio Transcription
  • Elevenlabs
  • Mcp Resources
  • Speech Synthesis
  • Voice Design

Overview

Output delivery is an important part of this ElevenLabs integration. The default behavior writes generated material to disk and reports its location, but a resource-only setting returns the content through MCP instead. Binary resources use base64 encoding, while text resources use UTF-8. A combined mode provides both forms, including later resource retrieval through the documented elevenlabs URI scheme. This gives a client without shared filesystem access an alternative to receiving unusable local paths. When relative paths are involved, a configurable base directory determines their location; the user's Desktop is the default.

This is the official ElevenLabs connection for assistants. Its documented audio tasks range from spoken output and voice cloning to recording transcription. The examples go beyond narration: they include designing character voices, transforming a recording's voice, generating an environmental soundscape, and distinguishing speakers in transcribed material. Clients mentioned include Windsurf and Cursor as well as Claude Desktop and OpenAI Agents. The quickstart uses uvx and an ElevenLabs API key, and tool usage requires account credits. An optional residency setting chooses a data region, but that capability is identified as enterprise-only. Setup guidance also addresses Windows Developer Mode and a missing uvx executable. Longer audio operations can hit timeouts in the development inspector even when the underlying work completes. The README does not enumerate tool identifiers; its capability examples therefore do not establish a named tool catalog.

Install & configure

Requirements

  • uv installed so the client can invoke uvx
  • ElevenLabs account credential
  • Credits available for ElevenLabs operations
  • Assistant or editor with MCP support
Documented launch / install command
uvx elevenlabs-mcp

The launch matches the Claude Desktop quickstart. Only the API key is needed from this environment list for the basic example; the other entries describe documented options. Windows setup calls for Claude Desktop Developer Mode. If uvx cannot be found, the troubleshooting section suggests configuring its absolute executable path.

Config file · macOS: ~/Library/Application Support/Claude/claude_desktop_config.json

Windows: %APPDATA%\Claude\claude_desktop_config.json

Use Settings → Developer → Edit Config when available. Do not assume a Linux configuration path; check the client documentation for your platform. Remote servers use the app’s connector flow when supported, not the local stdio file shown here. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Desktop configuration
{
  "mcpServers": {
    "elevenlabs-mcp": {
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "<credential from your ElevenLabs account>",
        "ELEVENLABS_MCP_BASE_PATH": "<optional root used when resolving relative file paths>",
        "ELEVENLABS_MCP_OUTPUT_MODE": "<optional delivery mode: files, resources, or both>",
        "ELEVENLABS_API_RESIDENCY": "<optional region for enterprise data residency>"
      }
    }
  }
}

Read the Claude Desktop setup guide

Config file · Project: .cursor/mcp.json

User: ~/.cursor/mcp.json

The project path is relative to the workspace root. The tilde denotes your user home directory. Use Cursor’s MCP settings to confirm which configuration and scope your installed version is reading. Merge this example with existing settings; do not overwrite unrelated servers.

Cursor configuration
{
  "mcpServers": {
    "elevenlabs-mcp": {
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "<credential from your ElevenLabs account>",
        "ELEVENLABS_MCP_BASE_PATH": "<optional root used when resolving relative file paths>",
        "ELEVENLABS_MCP_OUTPUT_MODE": "<optional delivery mode: files, resources, or both>",
        "ELEVENLABS_API_RESIDENCY": "<optional region for enterprise data residency>"
      }
    }
  }
}

Read the Cursor setup guide

Config file · Workspace: .vscode/mcp.json

For user scope, use the “MCP: Open User Configuration” command if available. Do not guess a user configuration path across operating systems, profiles, containers, or remote workspaces; check the client documentation. Merge this example with existing settings; do not overwrite unrelated servers.

VS Code configuration
{
  "servers": {
    "elevenlabs-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "<credential from your ElevenLabs account>",
        "ELEVENLABS_MCP_BASE_PATH": "<optional root used when resolving relative file paths>",
        "ELEVENLABS_MCP_OUTPUT_MODE": "<optional delivery mode: files, resources, or both>",
        "ELEVENLABS_API_RESIDENCY": "<optional region for enterprise data residency>"
      }
    }
  }
}

Read the VS Code setup guide

Config file · macOS/Linux: ~/.codeium/windsurf/mcp_config.json

Windows: %USERPROFILE%\.codeium\windsurf\mcp_config.json

Open the MCP configuration through Windsurf’s settings when possible to confirm the active file. Paths can differ in managed or future releases; check the client documentation if this location is not present. Merge this example with existing settings; do not overwrite unrelated servers.

Windsurf configuration
{
  "mcpServers": {
    "elevenlabs-mcp": {
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "<credential from your ElevenLabs account>",
        "ELEVENLABS_MCP_BASE_PATH": "<optional root used when resolving relative file paths>",
        "ELEVENLABS_MCP_OUTPUT_MODE": "<optional delivery mode: files, resources, or both>",
        "ELEVENLABS_API_RESIDENCY": "<optional region for enterprise data residency>"
      }
    }
  }
}

Read the Windsurf setup guide

Config file · Project scope: .mcp.json at the repository root

The project file uses mcpServers. For user scope, use claude mcp add --scope user rather than assuming .mcp.json in your home directory is the user configuration. Check the client documentation for managed settings and storage details. Merge this example with existing settings; do not overwrite unrelated servers.

Claude Code configuration
{
  "mcpServers": {
    "elevenlabs-mcp": {
      "type": "stdio",
      "command": "uvx",
      "args": [
        "elevenlabs-mcp"
      ],
      "env": {
        "ELEVENLABS_API_KEY": "<credential from your ElevenLabs account>",
        "ELEVENLABS_MCP_BASE_PATH": "<optional root used when resolving relative file paths>",
        "ELEVENLABS_MCP_OUTPUT_MODE": "<optional delivery mode: files, resources, or both>",
        "ELEVENLABS_API_RESIDENCY": "<optional region for enterprise data residency>"
      }
    }
  }
}

Read the Claude Code setup guide

Examples are translated from the published configuration. Supply your own credentials and verify requirements in the upstream README. Remote connectors are shown only where a supported configuration format is known.

Tools

No individual tool names were confirmed in the source material. Check the repository for its current tool list.

Names, permissions, and defaults can change. Check the current upstream documentation before granting access.

Use cases

  • Develop character voices by requesting variants before choosing one for a voice library.
  • Convert written material into spoken audio from an assistant conversation.
  • Work with transcription and speaker distinctions from recorded speech.
  • Deliver generated audio to an MCP client that cannot read the server's local files.

Strengths

  • The integration is published as ElevenLabs' official MCP server.
  • Output delivery can match local-file workflows or resource-only clients.
  • The README covers account setup, client configuration, and practical troubleshooting.

Limitations

  • Calling the audio capabilities depends on an API credential and available ElevenLabs credits.
  • Regional data residency is restricted to enterprise use.
  • Some lengthy requests can exceed development-inspector time limits.

Frequently asked questions

The server saves generated files and reports their paths. Relative file operations use the Desktop as their base unless configured otherwise.

Binary content is encoded as base64 in MCP resources. Text content uses UTF-8, and combined delivery also preserves disk output.

No. The README explicitly warns that using these operations needs ElevenLabs credits, in addition to the API key used for access.

Not stated in the README. Only capability summaries and sample requests are supplied, so individual identifiers cannot be listed.

Independent listing, not an affiliation or security review. Grant the least access needed and verify the upstream instructions before running code.

Related MCP servers

MiniMax MCP

AI Models & Agents

MiniMax MCP exposes MiniMax media APIs to compatible AI clients for speech, voice work, images, video, and music. It supports local stdio use and SSE deployment, with region-specific API credentials and configurable resource output.

pythonstdio1,590 GitHub stars

Just Prompt

AI Models & Agents

Just Prompt lets an MCP assistant consult several language models and preserve their answers. Alongside parallel prompting, it offers a panel workflow in which a designated model makes a decision after reviewing other responses.

pythonstdio739 GitHub stars

DeepSeek MCP Server

AI Models & Agents

DeepSeek MCP Server exposes DeepSeek V4 generation and account utilities to MCP clients. It offers chat, fill-in-the-middle completion, model discovery, balance checks, and in-process conversation management.

nodestdio353 GitHub stars

mcp-sequentialthinking-tools

AI Models & Agents

mcp-sequentialthinking-tools records stepwise reasoning with session history, branches, and revision metadata. It validates model-authored tool plans against a supplied tool list rather than discovering or choosing tools itself.

nodestdio587 GitHub stars