Pronounce

Overview

Pronounce is a Model Context Protocol server that settles how engineers actually pronounce developer jargon. With over 1848 sourced entries covering everything from kubectl to nginx to GIF, it brings a crowdsourced pronunciation guide directly into your AI assistant, letting you look up the correct way to say technical terms on the fly.

The server runs locally on your machine as a Python package installed via uvx pronounce-mcp. It communicates over stdio and requires no authentication—just install and start using it. Pronounce v0.1.1 is published under the MIT license with source code available at anzy-renlab-ai/pronounce on GitHub, where the project has 37 stars.

Pronounce sits in the Development category on mcp.site and works with MCP clients including Claude Desktop, Claude Code, Cursor, VS Code, Windsurf, and Zed. If you maintain this project, you can claim this listing to verify ownership and keep the information up to date.

Installation

// claude_desktop_config.json
{
  "mcpServers": {
    "pronounce": {
      "command": "uvx",
      "args": [
        "pronounce-mcp"
      ]
    }
  }
}