Video MCP Server

Analyze any video (file, URL, or Jira attachment) into frames + transcript for Claude Code

Local serverstdioPython

What is the Video MCP server?

Connect Video to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Analyze any video (file, URL, or Jira attachment) into frames + transcript for Claude Code. The video mcp server is what makes that connection.

What the server does

An MCP server that gives Claude Code the ability to analyze any video — a local file or a URL — through one set of tools.

Available tools

The toolset is worth reading before you wire it up, because it tells you what the integration is really for:

  • analyze_video — frames + transcript + metadata (the main tool). frame_interval
  • get_video_transcript_only — transcript text only
  • extract_frames_at — frames at specific timestamps ("00:42", "1:05", 12.5)
  • list_recent_analyses — cached analyses + backend used

Credentials and setup notes

Configuration is passed through the environment: VIDEO_MCP_ENV, OPENAI_API_KEY, GROQ_API_KEY, GEMINI_API_KEY, VIDEO_MCP_WHISPER_MODEL_PATH. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.

Installation

Installation goes through your MCP client rather than a global install: point it at video-vision-mcp on PyPI and it is fetched when the client starts. The copy-paste blocks for Claude Desktop, Claude Code and Cursor are further down this page.

Where it fits

This sits in the planning and project tracking group, where several servers overlap in what they claim to do but differ sharply once you actually set them up. Video's toolset — analyze_video, get_video_transcript_only, extract_frames_at and 1 more — is a fair guide to whether it matches your workflow. It is maintained by KitDevUA; worth a glance at recent repository activity before you build anything load-bearing on it.

This entry was verified against Video's own documentation before publication; SyncDev keeps the directory reviewed rather than auto-generated.

Worth knowing first

  • It runs with your machine's permissions. That is convenient and also the reason to think about what you point it at before you approve a tool call.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • Keep per-call confirmation enabled while you learn its behaviour; it is the cheapest safeguard you have.

Available tools

ToolWhat it does
analyze_videoframes + transcript + metadata (the main tool). frame_interval
get_video_transcript_onlytranscript text only.
extract_frames_atframes at specific timestamps ("00:42", "1:05", 12.5).
list_recent_analysescached analyses + backend used.

How to install the Video MCP server

{
  "mcpServers": {
    "video-vision": {
      "command": "uvx",
      "args": ["video-vision-mcp"],
      "env": {
        "VIDEO_MCP_ENV": "your-value",
        "OPENAI_API_KEY": "your-value",
        "GROQ_API_KEY": "your-value",
        "GEMINI_API_KEY": "your-value",
        "VIDEO_MCP_WHISPER_MODEL_PATH": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
VIDEO_MCP_ENVConfiguration value read at startup.Optional
OPENAI_API_KEYCredential the server authenticates with.Yes
GROQ_API_KEYCredential the server authenticates with.Yes
GEMINI_API_KEYCredential the server authenticates with.Yes
VIDEO_MCP_WHISPER_MODEL_PATHFilesystem location the server is allowed to use.Optional

Example prompts to try

  • Use Video to analyze video.
  • Use Video to get video transcript only.
  • Use Video to extract frames at.

Frequently asked questions

It connects Video to MCP-compatible AI assistants such as Claude and Cursor, exposing 4 tools (analyze_video, get_video_transcript_only, extract_frames_at, and more) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Video directly.