mcp-say MCP Server

Adds Text-to-Speech to things like Claude Desktop and Cursor IDE.

Local serverstdio

What is the mcp-say MCP Server?

mcp-say is an MCP project maintained in the blacktop/mcp-say repository. The maintainer describes its purpose as “Adds Text-to-Speech to things like Claude Desktop and Cursor IDE”. Read the project documentation for the complete scope.

Local setup

The project provides a local client configuration using mcp-tts. Follow the repository’s build and installation steps before copying it, and replace example paths with the paths on your own computer.

Configuration values

The example declares ELEVENLABS_API_KEY, ELEVENLABS_VOICE_ID, GOOGLE_AI_API_KEY, OPENAI_API_KEY, OPENAI_TTS_INSTRUCTIONS, MCP_TTS_SUPPRESS_SPEAKING_OUTPUT, MCP_TTS_ALLOW_CONCURRENT. Secret-looking values have been replaced with placeholders. Required and optional labels are shown only when the documentation states them.

Source

Project documentation · Repository · Discovery listing. This profile records the public documentation checked on 2026-10-08.

How to install the mcp-say MCP Server

{
  "mcpServers": {
    "say": {
      "command": "mcp-tts",
      "env": {
        "ELEVENLABS_API_KEY": "YOUR_ELEVENLABS_API_KEY",
        "ELEVENLABS_VOICE_ID": "EXAVITQu4vr4xnSDxMaL",
        "GOOGLE_AI_API_KEY": "YOUR_GOOGLE_AI_API_KEY",
        "OPENAI_API_KEY": "YOUR_OPENAI_API_KEY",
        "OPENAI_TTS_INSTRUCTIONS": "Speak in a cheerful and positive tone",
        "MCP_TTS_SUPPRESS_SPEAKING_OUTPUT": "true",
        "MCP_TTS_ALLOW_CONCURRENT": "false"
      }
    }
  }
}

From the project documentation. Replace placeholders and example paths before connecting.

Configuration

VariableDescriptionRequired
ELEVENLABS_API_KEYDeclared in the maintainer’s client configuration.Yes
ELEVENLABS_VOICE_IDDeclared in the maintainer’s client configuration.Optional
GOOGLE_AI_API_KEYDeclared in the maintainer’s client configuration.Yes
OPENAI_API_KEYDeclared in the maintainer’s client configuration.Yes
OPENAI_TTS_INSTRUCTIONSDeclared in the maintainer’s client configuration.Optional
MCP_TTS_SUPPRESS_SPEAKING_OUTPUTDeclared in the maintainer’s client configuration.Optional
MCP_TTS_ALLOW_CONCURRENTDeclared in the maintainer’s client configuration.Check documentation