Macwhisper MCP Server runs on your own machine — the client starts it, so there is no endpoint to ping. 116 installs a week from pypi. Last commit 17 Aug 2026.
MacWhisper transcription for Claude Desktop. Fully local, no cloud, audio stays on your Mac.
We read the source, 21 h ago · rules 3dff92dd89df
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.
proc = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.PIPE, text=True)
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 macwhisper-mcp-server -- uvx macwhisper-mcp-server
{
"mcpServers": {
"macwhisper-mcp-server": {
"args": [
"macwhisper-mcp-server"
],
"command": "uvx"
}
}
}
[mcp_servers.macwhisper-mcp-server]
command = "uvx"
args = ["macwhisper-mcp-server"]
{
"mcpServers": {
"macwhisper-mcp-server": {
"args": [
"macwhisper-mcp-server"
],
"command": "uvx"
}
}
}
{
"mcpServers": {
"macwhisper-mcp-server": {
"args": [
"macwhisper-mcp-server"
],
"command": "uvx"
}
}
}
This one needs environment variables set before it will start:
MACWHISPER_ALLOWED_PATHS (Colon-separated list of directories the server may read audio files from (e.g. ~/Desktop:~/Downloads)), MACWHISPER_CLI (Path to the mw binary. Auto-detected from /Applications/MacWhisper.app if omitted.), MACWHISPER_LOG_PATH (Log file path. Defaults to ~/Library/Logs/macwhisper-mcp.log).
The author declared them in the registry entry; get the values from the project itself.
Local audio transcription using whisper.cpp. Transcribe with OpenAI Whisper models.
Read-only MCP for FormLab — talk to your local lab notebook via Claude. Data stays local.
MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper
MCP server for local speech translation (EN ↔ 中文) via Whisper + Claude + Piper
Local MCP server for meeting transcripts, summaries, action items & decisions — no cloud.
Local NLLB translation for 200+ languages. Zero cloud, zero cost, runs entirely on your machine.
Persistent memory + decision tracking for Claude across sessions. Local SQLite, no cloud.
Local task scheduler and worker manager with MCP integration for Claude Desktop.
Answers built from our own checks of this server.