Paxa Labs runs on your own machine — the client starts it, so there is no endpoint to ping. 335 installs a week from npm. Last commit 5 Nov 2026.
Thai, English, Mandarin speech AI: TTS with playback, transcription, translation, OCR, extraction
We read the source, 1 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
return spawnSync(probe, [command], { stdio: "ignore" }).status === 0;
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp -e 'PAXA_API_KEY=<PAXA_API_KEY>' -- npx -y @paxalabs/mcp
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@paxalabs/mcp"
],
"env": {
"PAXA_API_KEY": "<PAXA_API_KEY>"
}
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@paxalabs/mcp"]
env = { PAXA_API_KEY = "<PAXA_API_KEY>" }
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"@paxalabs/mcp"
],
"env": {
"PAXA_API_KEY": "<PAXA_API_KEY>"
}
}
}
}
{
"servers": {
"mcp": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@paxalabs/mcp"
],
"env": {
"PAXA_API_KEY": "<PAXA_API_KEY>"
}
}
}
}
Put your own value in place of
<PAXA_API_KEY> (Paxa Labs API key, created at https://paxalabs.com/app/keys).
The author’s registry entry marks it as required.
Optional settings from the registry entry, left out of the block above:
PAXA_OUTPUT_DIR (Directory where text_to_speech and dialogue_to_speech save files (default: the working directory)), PAXA_DEFAULT_VOICE (Voice id used when a call does not pick one (default: foithong)).
OCR, transcription, file extraction, and image generation for AI agents via MCP.
Extract local PDF text with page-level paragraphs and English/German OCR fallback.
Extracts PDF text locally, with macOS PDFKit and Vision OCR fallbacks and optional AI retry.
OCR, editable Word, tables, translation and data extraction for Arabic-script documents
EU-hosted AI platform: OpenAI-compatible LLM gateway, document extraction, transcription, agents.
Extract PDFs to Markdown, RAG chunks and cited tables; publish tracked Doc Links with read stats.
Arabic-first OCR, translation and document extraction. First call mints a free trial key.
PDF tools for agents: compress to a size, Arabic + English OCR, Office conversion, JSON extraction.
Answers built from our own checks of this server.