extract_video_frames
Record screen and extract key frames from an Android device (Layers 1+2). Uses adb screenrecord then ffmpeg scene-filtered JPEG extraction. CRITICAL: uses -pix_fmt yuvj420p for ffmpeg 8.x compatibility. Falls back to regular fps extraction if scene filter produces 0 frames.
This record as markdown: /tools/io-github-homenshum-nodebench/extract-video-frames.md
What extract_video_frames does on Nodebench
AI agents invoke extract_video_frames to trigger actions in Nodebench. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
Why extract_video_frames is rated High
This tool executes external system commands (adb screenrecord, ffmpeg) on an Android device to capture screen content and extract frames. It triggers real device operations via adb and runs media processing pipelines, making it an Execute category tool. Severity is high because it can capture sensitive screen content from a connected device and involves external command execution with potential for misuse.
From the tool's definition 'Record screen and extract key frames from an Android device (Layers 1+2). Uses adb screenrecord then ffmpeg scene-filtered JPEG extraction.'
Attacks that exploit this kind of access
The rule that runs extract_video_frames safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For extract_video_frames, this is the rule to start with:
extract_video_frames stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every extract_video_frames call is checked against it from then on.
Questions about extract_video_frames
Record screen and extract key frames from an Android device (Layers 1+2). Uses adb screenrecord then ffmpeg scene-filtered JPEG extraction. CRITICAL: uses -pix_fmt yuvj420p for ffmpeg 8.x compatibility. Falls back to regular fps extraction if scene filter produces 0 frames. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for extract_video_frames: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Nodebench. Nothing to install.
extract_video_frames is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the extract_video_frames rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for extract_video_frames. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
extract_video_frames is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
Across the catalogue