Ollos MCP runs on your own machine — the client starts it, so there is no endpoint to ping. 57 installs a week from npm. Last commit 16 Sep 2026.
Local, offline transcription, speakers, keyframes, on-screen text and review of any audio or video.
We read the source, 20 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.
return path.join(ensureDir(path.join(this.root, namespace, key)), filename)
const child = spawn(bin, args, { windowsHide: true, stdio: ['ignore', 'pipe', 'pipe'] })
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 ollos-mcp -- npx -y ollos-mcp
{
"mcpServers": {
"ollos-mcp": {
"args": [
"-y",
"ollos-mcp"
],
"command": "npx"
}
}
}
[mcp_servers.ollos-mcp]
command = "npx"
args = ["-y", "ollos-mcp"]
{
"mcpServers": {
"ollos-mcp": {
"args": [
"-y",
"ollos-mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"ollos-mcp": {
"args": [
"-y",
"ollos-mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
OLLOS_HOME (Where jobs, cache and models live. Default ~/.ollos), OLLOS_OFFLINE (Set to 1 to forbid any network access (models must be warmed up first)), OLLOS_YTDLP (Path to a yt-dlp binary for video-site URLs (default: found on PATH)), OLLOS_YTDLP_ARGS (Allow-listed yt-dlp flags, e.g. --no-check-certificates behind a TLS-intercepting proxy).
The author declared them in the registry entry; get the values from the project itself.
Local MCP server to analyze video, audio & images: frames, transcripts, on-screen text.
Video knowledge base for agents: search your library's transcripts, keyframes and on-screen text.
Transcribe Russian audio and video with timestamps and optional speaker labels from files or links.
Search your dictation transcripts and transcribe audio or video on-device, with speaker labels.
Download any video from a URL, or get its transcript and key frames. All local, no API keys.
Offline speech-to-text & speaker diarization MCP server: transcribe audio on-device, no cloud
Analyze any video (local file or URL) into frames + transcript for Claude Code
Verbatim transcription of public video/audio URLs to clean text, SRT, and timestamped records.
Answers built from our own checks of this server.