mediasense runs on your own machine — the client starts it, so there is no endpoint to ping. 923 installs a week from pypi. Last commit 7 Nov 2026.
Let Claude listen to audio and watch video: transcribe, summarize and edit recordings and links.
Today is the operative word: we check mediasense every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
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 mediasense -- uvx mediasense
{
"mcpServers": {
"mediasense": {
"command": "uvx",
"args": [
"mediasense"
]
}
}
}
[mcp_servers.mediasense]
command = "uvx"
args = ["mediasense"]
{
"mcpServers": {
"mediasense": {
"command": "uvx",
"args": [
"mediasense"
]
}
}
}
{
"servers": {
"mediasense": {
"type": "stdio",
"command": "uvx",
"args": [
"mediasense"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
MEDIASENSE_COOKIES_FROM_BROWSER (Optional: browser to read cookies from (chrome, firefox, edge…) for links that need a login).
Connect Claude to Fathom meeting recordings, transcripts, and summaries
Translate documents, subtitles, pictures, audio and video with layout kept; transcribe recordings.
Secure audio transcription meets AI. Connect Alice recordings to Claude, ChatGPT, Gemini, and more.
Transcribe, summarize and analyze audio with AssemblyAI speech-to-text and Speech Understanding.
Summarize and transcribe videos, audio, documents and web pages; subtitles; search your library.
Read screen recording links: summaries, transcripts, suggested changes and frame images.
Search and read your LiteScribe recordings: transcripts, summaries, action items, screenshots.
Transcribe audio and video with Speechmatics speech-to-text from Claude and any MCP client.
Answers built from our own checks of this server.