Boson Video runs on your own machine — the client starts it, so there is no endpoint to ping. 90 installs a week from pypi. Last commit 15 Oct 2026.
Let your AI read any video: timed transcript, full-resolution frames, screen text, claim checks.
What the code does
We read the source, 4 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.
done = subprocess.run(cmd, capture_output=True, text=True, encoding="utf-8", errors="replace")
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
This code can reach further than it looks
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.
Connect this server
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 boson-video -- uvx boson-video{
"mcpServers": {
"boson-video": {
"command": "uvx",
"args": [
"boson-video"
]
}
}
}[mcp_servers.boson-video]
command = "uvx"
args = ["boson-video"]{
"mcpServers": {
"boson-video": {
"command": "uvx",
"args": [
"boson-video"
]
}
}
}{
"servers": {
"boson-video": {
"type": "stdio",
"command": "uvx",
"args": [
"boson-video"
]
}
}
}Optional settings from the registry entry, left out of the block above:
TYPESAFE_API_KEY (Optional. Jev checks claims by meaning; without it, code checks the numbers).
Alternatives to Boson Video
same job, measured the same wayTurn any YouTube video into text: transcript, title, channel, timestamps.
Video knowledge base for agents: search your library's transcripts, keyframes and on-screen text.
Local, offline transcription, speakers, keyframes, on-screen text and review of any audio or video.
Transcribe audio and video into timestamped transcripts, and search and read your transcripts.
Extract YouTube transcripts, search what was said, and read on-screen frames with cited timestamps.
Hand any social video to your AI agent — frames + transcript bundled. MCP server for watch-cli.
Local MCP server to analyze video, audio & images: frames, transcripts, on-screen text.
Let an AI watch a video: timestamped transcript, scene-selected keyframes and exact frames. Local.
Boson Video — questions
Answers built from our own checks of this server.