MCP servers · azzy-h

Video Frames: MCP server for timecoded video frames and metadata

Local MCP server that lets image-only models view timecoded video frames and read video metadata.

This text was machine-translated from the publisher's own information and has not been checked by a human editor. The publisher's original text is the reference.

This resource was imported automatically from the sources listed below and has not been reviewed by the AI Gate team yet. The description is the publisher's own, as published. Check the repository before installing.

What it does

The server provides two tools. view_frames samples a time range and returns frames as images, each preceded by its timecode, with adjustable interval, frame count, edge size, format and JPEG quality. Setting start and end to the same value inspects a single moment. video_info returns container metadata, and with detail="full" also runs a whole-file scan for scene cuts, silences and EBU R128 loudness.

It suits a model that accepts image input and needs to examine video at specific times, or that needs measurable properties such as scene changes, silences or loudness. Because each image is paired with its timecode, the order of events can be reasoned about.

The server runs locally and is not hosted, so a client must be pointed at it. It requires Python 3.10 or newer and ffmpeg, with ffprobe optional (without it, fewer metadata fields are returned). A setup script creates a project virtual environment, and a doctor command checks the environment. The per-call image limit is set by MCP_VIDEO_MAX_IMAGES, default 20. Requests over the limit fail rather than being truncated, and results are cached on disk.

Limitations and requirements

The model used with the client must accept image input; otherwise returned frames are dropped or reduced to text. The server is local and must be configured in a client manually. Python 3.10 or newer is required, and ffmpeg is required (ffprobe is optional, with reduced metadata without it). Requests exceeding the image limit fail entirely.

Safety

Our team has not reviewed this resource. Only automated rules checked it; resources with high-risk signals are not published. These are signals, not a guarantee that installing it is safe. Try it in a sandbox project first.

  • Runs code or changes an assistant's behaviour

Sources

  • Official MCP Registry first seen 13 Nov 2026 · last seen 13 Nov 2026 · its page on the source
    Video Frames

    MCP server that lets image-only models look at video: timecoded frames, measurable properties.

    v0.1.1
    As shown on registry.modelcontextprotocol.io when we last read it
MCP servers
cloudflare

Cloudflare MCP servers

Cloudflare's hosted MCP servers for its products: documentation search, sandbox containers, browser rendering, Radar internet data, logs and analytics, Workers and more.

4.5K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026
MCP servers
redis

Redis MCP Server

Redis's official MCP server that lets an AI assistant store, read and search data in a Redis database, including streams, JSON documents and vector indexes.

642 GitHub starsData & databasesSoftware development
Updated 17 Nov 2026
MCP servers
microsoft

Playwright MCP (browser automation)

Microsoft's MCP server that lets an AI assistant open web pages, click, type and read them through a real browser, using the page structure instead of screenshots.

39.6K GitHub starsTesting & QAWeb, search & browser
Updated 17 Nov 2026
MCP servers
hashicorp

Terraform MCP Server (HashiCorp)

HashiCorp's MCP server that gives an assistant current Terraform Registry information on providers, modules and policies, and can manage HCP Terraform workspaces.

1.6K GitHub starsCloud & DevOpsSoftware development
Updated 17 Nov 2026