🐍 🏠 - MCP Server that uses the open weight Kokoro TTS models to convert text-to-speech. Can convert text to MP3 on a local driver or auto-upload to an S3 bucket.
Install
npx -y mberg-kokoro-tts-mcpRequired environment variables
AWS_ACCESS_KEYSet in your MCP configAWS_SECRET_ACCESS_KEYSet in your MCP configclaude_desktop_config.json
{
"mcpServers": {
"mberg-kokoro-tts-mcp": {
"command": "npx",
"args": [
"-y",
"mberg-kokoro-tts-mcp"
],
"env": {
"AWS_ACCESS_KEY": "<YOUR_AWS_ACCESS_KEY>",
"AWS_SECRET_ACCESS_KEY": "<YOUR_AWS_SECRET_ACCESS_KEY>"
}
}
}
}Add this to your Claude Desktop config file. Find it at ~/Library/Application Support/Claude/claude_desktop_config.json on macOS.
What this does
mberg/kokoro-tts-mcp exposes a set of tools to Claude over the Model Context Protocol. After you add it to claude_desktop_config.json (snippet above) and restart Claude Desktop, those tools become callable inside any conversation. That makes it useful when you want Claude to reach into the local or remote filesystem without copy-pasting context every turn.
Requirements
This server needs the following environment variables to be set before it can run:
AWS_ACCESS_KEY AWS_SECRET_ACCESS_KEY
Set these via the env object in your MCP config (see claude_desktop_config.json snippet above).
Common use cases
- •Read, search, and edit files across local or remote storage
- •Convert between file formats (markdown, PDF, docx, and similar)
- •Drive bulk renames, organization, or archival from a chat session
More Python MCP servers
microsoft/markitdown
🎖️ 🐍 🏠 - MCP tool access to MarkItDown -- a library that converts many file formats (local or remote) to Markdown for LLM consumption.
mindsdb/mindsdb
Connect and unify data across various platforms and databases with .
eyaltoledano/claude-task-master
📇 ☁️ 🏠 - AI-powered task management system for AI-driven development. Features PRD parsing, task expansion, multi-provider support (Claude, OpenAI, Gemini, Perplexity, xAI), and selective tool loadi
FastMCP
🐍 - A high-level framework for building MCP servers in Python