Paxa Labs — Claude Code MCP server: features and setup
This MCP server gives an agent speech, transcription, translation, OCR, and document-field extraction tools for local work.
claude mcp add --env PAXA_API_KEY=<PAXA_API_KEY> --env PAXA_OUTPUT_DIR=<PAXA_OUTPUT_DIR> --env PAXA_DEFAULT_VOICE=<PAXA_DEFAULT_VOICE> --transport stdio paxa-labs -- npx -y @paxalabs/mcpWhat Paxa Labs does
Paxa Labs connects an agent to voice tools for spoken output and input. It can play short replies, process longer text through an audio queue, write speech to MP3, Opus, or WAV, and produce matching subtitles. Recording transcription supports speaker labels, word timings, and pause data for cutting.
The server also translates text into Thai, reads local PDFs and images with OCR, and fills typed fields from document scans. OCR accepts PDF, PNG, JPEG, and WebP files. A Paxa API key must be supplied as PAXA_API_KEY; without it, the server cannot connect. API calls consume credits, and the tool set is currently beta.
What it helps with
- play an agent response through local speakers
- save generated speech as an audio file
- transcribe a recording with subtitles
- read a PDF or image with OCR
- fill typed fields from a scanned document
Example prompts for the agent
- Read the change summary aloud with
speak. - Transcribe
meeting.mp4with speaker labels and subtitles. - Extract dates, amounts, and bank details from
invoice.pdf.
How to install Paxa Labs
Platform CLI
claude mcp add --env PAXA_API_KEY=<PAXA_API_KEY> --env PAXA_OUTPUT_DIR=<PAXA_OUTPUT_DIR> --env PAXA_DEFAULT_VOICE=<PAXA_DEFAULT_VOICE> --transport stdio paxa-labs -- npx -y @paxalabs/mcpReplace <…> with your own values
Platform CLI
codex mcp add paxa-labs --env PAXA_API_KEY=<PAXA_API_KEY> --env PAXA_OUTPUT_DIR=<PAXA_OUTPUT_DIR> --env PAXA_DEFAULT_VOICE=<PAXA_DEFAULT_VOICE> -- npx -y @paxalabs/mcpReplace <…> with your own values
Config file
{
"mcpServers": {
"paxa-labs": {
"command": "npx",
"args": [
"-y",
"@paxalabs/mcp"
],
"env": {
"PAXA_API_KEY": "<PAXA_API_KEY>",
"PAXA_OUTPUT_DIR": "<PAXA_OUTPUT_DIR>",
"PAXA_DEFAULT_VOICE": "<PAXA_DEFAULT_VOICE>"
}
}
}
}Replace <…> with your own values
Config file
{
"servers": {
"paxa-labs": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@paxalabs/mcp"
],
"env": {
"PAXA_API_KEY": "<PAXA_API_KEY>",
"PAXA_OUTPUT_DIR": "<PAXA_OUTPUT_DIR>",
"PAXA_DEFAULT_VOICE": "<PAXA_DEFAULT_VOICE>"
}
}
}
}Replace <…> with your own values
Platform CLI
gemini mcp add -e PAXA_API_KEY=<PAXA_API_KEY> -e PAXA_OUTPUT_DIR=<PAXA_OUTPUT_DIR> -e PAXA_DEFAULT_VOICE=<PAXA_DEFAULT_VOICE> paxa-labs npx -y @paxalabs/mcpReplace <…> with your own values
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about Paxa Labs
How do I install Paxa Labs in Claude Code?
Run claude mcp add mcp -e PAXA_API_KEY=<PAXA_API_KEY> -- npx -y @paxalabs/mcp.
What does Paxa Labs do?
It gives an agent tools for speech, recording transcription, Thai translation, OCR, and typed-field extraction from local documents.
Which files can its OCR tool process?
ocr_document accepts local PDF, PNG, JPEG, and WebP files, then returns Markdown or structured blocks.
