Claude Real Video runs on your own machine — the client starts it, so there is no endpoint to ping. 1 561 installs a week from pypi. Last commit 8 Oct 2026.
Let any LLM watch a video locally — and search everything it has ever watched.
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.
p = subprocess.Popen(cmd, stdout=subprocess.PIPE, stderr=subprocess.STDOUT, text=True, errors="replace")
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 claude-real-video -- uvx claude-real-video
{
"mcpServers": {
"claude-real-video": {
"command": "uvx",
"args": [
"claude-real-video"
]
}
}
}
[mcp_servers.claude-real-video]
command = "uvx"
args = ["claude-real-video"]
{
"mcpServers": {
"claude-real-video": {
"command": "uvx",
"args": [
"claude-real-video"
]
}
}
}
{
"servers": {
"claude-real-video": {
"type": "stdio",
"command": "uvx",
"args": [
"claude-real-video"
]
}
}
}
Let AI agents watch videos: local transcripts, speakers, scenes, chapters and moment search
Web grounding for local & cloud LLMs: search, fetch, token-capped evidence packs, and research.
Your local project library: hand any AI a project pack, search it, and write findings back.
Transcribe videos from 1000+ platforms or local files offline, and search across every transcript
Search your own videos and photos by meaning and cut them into a video, 100% local.
Lets Claude and ChatGPT watch YouTube videos: what is seen and heard, answered with timestamps.
Local MCP server for isolated, evidence-backed GDWEB design analysis and web search.
Search that learns from feedback, over text and images: embeds locally, sends DNA only vectors.
Answers built from our own checks of this server.