ElevenLabs MCP Server
ElevenLabs text-to-speech and audio processing for your AI assistant.
Data last scanned today · Reviewed yesterday
Overview
This server integrates ElevenLabs audio capabilities directly into MCP-compatible clients such as Claude Desktop, Cursor, and Windsurf. It allows AI models to perform tasks like voice cloning, audio transcription, and high-quality speech synthesis by interfacing with the ElevenLabs API. Installation is managed via Python-based tools like uv or pip. Once configured with an ElevenLabs API key, users can prompt their AI to generate specific voice variations or create characters with specialized speech profiles directly within their development or chat environment.
Our verdict
With a security score of 38/100, this server is classified as high-risk. The primary security concern is the total lack of an authentication method, meaning any configuration access allows full use of the tool. Additionally, the server operates without a read-only mode, granting broad write access to any connected client. Given these vulnerabilities, this project is recommended only for users who can carefully manage their API key environment variables and strictly limit the scope of the clients they connect.
- Zero direct dependencies minimizes the supply-chain attack surface
- Supported by 21 active contributors
- Comprehensive README documentation facilitates quick setup
- No authentication method for client connections
- Full write access granted upon installation without read-only restrictions
- Community-maintained rather than officially managed by ElevenLabs
Compatibility
| Client | Local | Docker | Remote | Read-only |
|---|---|---|---|---|
| ChatGPT | ||||
| Claude Desktop | ||||
| Cursor | ||||
| VS Code | ||||
| Windsurf |
Frequently asked questions
›What prerequisites are needed to run the ElevenLabs MCP server?
You need an ElevenLabs API key and the uv Python package manager installed. ElevenLabs provides a free tier that includes 10,000 credits per month.
›How do I configure the server for Windows Claude Desktop?
You must enable Developer Mode by selecting the Help menu in the top left corner of the Claude Desktop application before configuring the MCP server.
›Can I control where generated audio files are saved?
Yes, you can specify the target directory by setting the ELEVENLABS_MCP_BASE_PATH environment variable, which defaults to your Desktop.
›How can I receive audio data directly in the MCP response instead of as a saved file?
You can change the ELEVENLABS_MCP_OUTPUT_MODE environment variable to 'resources'. This approach is recommended for serverless or containerized environments where file system access might be restricted.
›Is it possible to specify a data residency region?
Yes, you can use the ELEVENLABS_API_RESIDENCY environment variable to set your region, which defaults to 'us'. Note that this is an enterprise-only feature.
Alternatives
Changelog
Badge
Maintain this server? Add the live badge to your README.