whosaid runs on your own machine — the client starts it, so there is no endpoint to ping. 917 installs a week from pypi. Last commit 25 Oct 2026.
Local speaker-attributed transcription and meeting search for Apple Silicon. Audio stays on the Mac.
We read the source, 1 h ago · rules 995398eba69f
Things with no honest explanation: a promise that contradicts the code, code that runs at install time while hiding what it does, data leaving the machine.
f"rm -rf {AGENT_DIR}",
out = subprocess.run(
env = dict(os.environ)
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.
p = subprocess.run([whosaid, *args], capture_output=True, text=True, timeout=timeout)
hook, shell=True, input=text, env=env,
env = dict(os.environ)
(p for p in folder.iterdir() if p.is_file() and p.suffix.lower() in AUDIO_EXTS),
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
Code changes quietly between releases, and nobody reads the diff of a dependency. We do, on every release — watch whosaid and you get told the day something new turns up.
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 whosaid -- uvx whosaid
{
"mcpServers": {
"whosaid": {
"command": "uvx",
"args": [
"whosaid"
]
}
}
}
[mcp_servers.whosaid]
command = "uvx"
args = ["whosaid"]
{
"mcpServers": {
"whosaid": {
"command": "uvx",
"args": [
"whosaid"
]
}
}
}
{
"servers": {
"whosaid": {
"type": "stdio",
"command": "uvx",
"args": [
"whosaid"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
WHOSAID_WORKSPACE (Absolute path to the meetings workspace the search tools read).
Read-only search over the meetings, dictations and writing saved by the Transcripted Mac app.
MacWhisper transcription for Claude Desktop. Fully local, no cloud, audio stays on your Mac.
The private, owned conversation-memory layer for AI. Record, transcribe, and search every meeting.
Search your dictation transcripts and transcribe audio or video on-device, with speaker labels.
Meeting transcripts for AI agents: search calls, read who said what, transcribe files and links.
Search and read locally-recorded meeting transcripts over stdio. Read-only, no network.
Search bills and speaker-attributed hearing transcripts across all 50 US state legislatures.
Search Japanese Diet bills and meeting transcripts (NDL Kokkai API) with source attribution.
Answers built from our own checks of this server.