video-vision-mcp
This MCP server enables Claude Code to analyze videos by converting them into sampled frame images and audio transcripts. It supports local files, URLs, and Jira attachments, utilizing backend tiers ranging from local ffmpeg/whisper to cloud ASR or native Gemini analysis depending on available API keys.
Package and access
Local package with source-attributed installation metadata. Koskamo does not execute packages during review.
What you can do with it
- Analyze a local video file to extract frames and transcript
- Process a video URL for visual and audio insights
- Review Jira bug ticket screen recordings via attachment download
- Get transcript-only output for audio-heavy videos
Source and maintenance
- Maintenance checked
Packages and installation
Source-provided package data. Koskamo has not executed or live-probed this package.
video-vision-mcp 0.5.1
{
"version": "0.5.1",
"transport": "stdio",
"identifier": "video-vision-mcp",
"runtimeHint": "uvx",
"registryType": "pypi",
"registryBaseUrl": "https://pypi.org",
"environmentVariables": [
{
"name": "VIDEO_MCP_ENV",
"description": "Optional path to a .env file with config (API keys, tuning)."
},
{
"name": "GEMINI_API_KEY",
"description": "Enables tier-3 native Gemini video analysis (default when set)."
},
{
"name": "OPENAI_API_KEY",
"description": "Enables tier-2 OpenAI Whisper transcription."
},
{
"name": "GROQ_API_KEY",
"description": "Enables tier-2 Groq whisper-large-v3 transcription."
}
]
}Tools
Reported by the attributed source; not independently observed by Koskamo.
Connect from your client
Each snippet configures the same source-provided package; replace placeholders before use.
Cursor
{
"mcpServers": {
"video-vision-mcp": {
"command": "uvx",
"args": [
"video-vision-mcp==0.5.1"
],
"env": {
"VIDEO_MCP_ENV": "<YOUR_VIDEO_MCP_ENV>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"GROQ_API_KEY": "<YOUR_GROQ_API_KEY>"
}
}
}
}Cline
{
"mcpServers": {
"video-vision-mcp": {
"command": "uvx",
"args": [
"video-vision-mcp==0.5.1"
],
"env": {
"VIDEO_MCP_ENV": "<YOUR_VIDEO_MCP_ENV>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"GROQ_API_KEY": "<YOUR_GROQ_API_KEY>"
}
}
}
}VS Code
{
"servers": {
"video-vision-mcp": {
"type": "stdio",
"command": "uvx",
"args": [
"video-vision-mcp==0.5.1"
],
"env": {
"VIDEO_MCP_ENV": "<YOUR_VIDEO_MCP_ENV>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"GROQ_API_KEY": "<YOUR_GROQ_API_KEY>"
}
}
}
}Claude Desktop
{
"mcpServers": {
"video-vision-mcp": {
"command": "uvx",
"args": [
"video-vision-mcp==0.5.1"
],
"env": {
"VIDEO_MCP_ENV": "<YOUR_VIDEO_MCP_ENV>",
"GEMINI_API_KEY": "<YOUR_GEMINI_API_KEY>",
"OPENAI_API_KEY": "<YOUR_OPENAI_API_KEY>",
"GROQ_API_KEY": "<YOUR_GROQ_API_KEY>"
}
}
}
}Let your agent find its tools
Find servers like video-vision-mcp from your agent. Add Koskamo once to search the index for endpoints, access requirements, and client setup. Public discovery needs no key.