Tools Overview
Video Context MCP exposes twelve tools that your AI coding assistant can call. The video-processing tools accept local file paths, file:// URIs, and remote http(s):// URLs. Remote videos are downloaded and cached automatically.
Video Analysis Tools
Section titled “Video Analysis Tools”| Tool | Description | Key Parameters |
|---|---|---|
analyze_video | Ask questions about video content | videoPath, question, provider? |
summarize_video | Generate a structured video summary | videoPath, provider? |
extract_frames | Extract frames from a video | videoPath, mode, count / intervalSec / timestamps / sceneThreshold, maxImages?, offset? |
search_timestamp | Find when something specific happens | videoPath, query, provider? |
get_video_info | Get video metadata — no AI required | videoPath |
transcribe_video | Transcribe audio/speech from a video | videoPath, provider?, language?, diarize?, translate?, outputFormat? |
Video Redaction Tool (Pro) ⚠️ Experimental
Section titled “Video Redaction Tool (Pro) ⚠️ Experimental”| Tool | Description | Key Parameters |
|---|---|---|
redact_sensitive | Blur, pixelate, or blackout sensitive regions | videoPath, intent? / regions?, effect?, detectionMode?, allowRemoteDetection?, previewOnly?, provider?, outputPath? |
Media Generation Tools (Pro) ⚠️ Experimental
Section titled “Media Generation Tools (Pro) ⚠️ Experimental”These tools are powered by the MiniMax API and require a Pro license (VIDEO_MCP_LICENSE_KEY) and a MINIMAX_API_KEY.
| Tool | Description | Key Parameters |
|---|---|---|
text_to_speech | Convert text to natural speech audio | text, model?, voice_id?, speed?, vol?, pitch?, emotion?, format? |
generate_image | Generate images from a text prompt | prompt, model?, aspect_ratio?, n?, prompt_optimizer? |
generate_video | Generate video from text/image prompt (returns task_id) | prompt?, model?, first_frame_image?, duration?, resolution?, prompt_optimizer? |
generate_music | Generate music from a prompt and optional lyrics | prompt, lyrics?, model?, is_instrumental?, lyrics_optimizer?, format? |
query_generation_task | Poll async video generation status + download result | task_id |
Supported Input Formats
Section titled “Supported Input Formats”| Format | Example |
|---|---|
| Local file path | ./demo.mp4, /home/user/recordings/clip.mp4 |
| Windows path | C:\Users\alice\Videos\demo.mp4 |
file:// URI | file:///home/user/videos/clip.mp4 |
| Remote HTTP/S URL | https://example.com/video.mp4 |
| YouTube URL | https://www.youtube.com/watch?v=abc123 |
| Other platforms | Vimeo, TikTok, Bilibili, etc. — requires Pro |
Choosing a Provider
Section titled “Choosing a Provider”Tools that use AI (analyze_video, summarize_video, search_timestamp, transcribe_video, and AI-assisted redact_sensitive) accept an optional provider parameter. When omitted, the server uses the configured default and falls back automatically if a provider is unavailable.
- Video providers: Gemini 3.5 Flash, MiniMax-M3, Kimi K2.6, Qwen3.7, MiMo-V2.5, GLM-4.6V → see Video Providers
- Audio providers: Deepgram, AssemblyAI, Groq/Whisper, Gemini → see Audio Providers
Quick Examples
Section titled “Quick Examples”Video analysis:
"Analyze the video at ./demo.mp4 — what happens in it?""Summarize ./long-video.mp4""Extract 5 frames from ./recording.mp4""At what timestamp does the person wave in ./clip.mp4?""Get metadata for ./video.mp4""Transcribe ./interview.mp4 with speaker diarization"Media generation (Pro):
"Read this paragraph aloud in a calm male voice.""Generate an image of a futuristic cityscape at night, 16:9.""Create a 6-second video of a golden retriever playing fetch on a beach.""Compose background music for a cooking video — warm, acoustic guitar, instrumental.""Check the status of video task 106916112212032."