Skip to content
Try it free

MCP server

Give your agent the video

A video MCP server for Claude, Cursor and Codex. Transcripts, summaries and timestamped answers, in a size an agent can afford.

Install itSee minutes and pricing

What it is

An MCP server that gives your agent a video as context: the outline first, then the exact moments it asks for. Without it, an agent cannot watch a link.

Install it in your client

The remote server is at https://scribiz.com/mcp. Full install guide

Nothing to install. Works from any machine.

No key. Captions, videos already processed, and a model read of the link within a small daily limit. No on-screen notes.

Terminal
$ claude mcp add --transport http scribiz https://scribiz.com/mcp

With an API key. Listen and Watch on new videos, using your minutes.

Terminal
$ claude mcp add --transport http scribiz https://scribiz.com/mcp --header "Authorization: Bearer $SCRIBIZ_API_KEY"

How it connects

Connection modes
ModeWhat you get
Remote, no keyPaste the URL and go. Captions when our server can read them, videos Scribiz already holds, and otherwise a model reads the link (times approximate, about 2 seconds, no speaker labels). About 10 minutes of reading a day, videos up to 15 minutes, 5 questions a day. No on-screen notes.
Remote, with an API keyListen, Watch and Both on any public video, from your minutes. The key goes in an Authorization header as a Bearer token and is the same key the API takes. Keys are made in the dashboard, after you sign in.
Local, scribiz mcpOne command, after npm install -g scribiz and scribiz login (or scribiz setup): claude mcp add scribiz -- scribiz mcp. It runs on your machine, with your free Scribiz account (30 minutes a month) or your own Gemini key, which uses no Scribiz minutes, and it fetches links from your own connection. It takes the watch argument and serves stored on-screen notes, like the remote server with a key. Local files work from folders you allow. Links to your own machine and to private networks are refused unless you pass --allow-private-network. Tested on macOS only.
OAuth sign-inFor claude.ai connectors. Not built yet, so claude.ai uses the keyless URL for now.

The tools

  • get_video_contextmay process a new video

    The outline of a video: summary, chapters and key moments with links.

  • get_transcriptmay process a new video

    The transcript or one stretch of it, paged, as text, Markdown, SRT, VTT or JSON.

  • ask_videomay process a new video

    A question about the video, answered with cited moments.

  • search_videomay process a new video

    Where a word or topic comes up, as ranked moments with timestamps.

  • get_jobfree

    The state of a long job, by its id.

All five are read only. Processing a new video spends minutes. Parameters and output shapes, what it costs your context and why transcripts are untrusted text.

Questions, answered

Model Context Protocol, an open standard that lets an AI app call tools. Scribiz runs an MCP server, so your agent can ask for a video instead of you pasting a transcript into the chat.

Claude Code, Claude Desktop, Cursor, VS Code and Codex, through a connection URL. claude.ai takes the URL as a custom connector. We have not tested ChatGPT yet, so we do not list it.

You do not need a key to start. Without one, the remote server uses captions when it can read them, answers at once for videos Scribiz has already processed, and otherwise has a model read the link. That is about 10 minutes of reading a day, for videos up to 15 minutes, and it never looks at the picture, so there are no on-screen notes. Looking at the picture needs an API key and uses minutes.

Most video MCP servers read YouTube captions and stop when there are none. When there are none, Scribiz has a model read the video from its link. It handles links beyond YouTube, and answers from a compact summary before it ever sends the transcript. Reading the picture needs an API key.

It can try. A transcript is text from a third party, and a video can say anything. Scribiz marks the content as untrusted data, wraps it in a labelled block and says so in the tool description. Treat it like any web page your agent reads, and keep tools that write or send behind a confirmation.

The link or the audio goes to Scribiz and then to Google for processing. Media is deleted when a job ends.

Keep going

The web tool runs the same engine and is the quickest way to see what a result looks like.