analyze_asset_intelligence
Analyze one local asset with traceable FFmpeg and optional Apple Vision evidence: technical metadata, brightness, saturation, loudness, scenes, semantic frame labels, non-identity face/person counts, filename/transcript tags, motion and quality. Never identifies a person.
This record as markdown: /tools/cutpilot/analyze-asset-intelligence.md
What analyze_asset_intelligence does on Cutpilot
AI agents call analyze_asset_intelligence to retrieve information from Cutpilot without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why analyze_asset_intelligence is rated Low
This tool retrieves and analyzes metadata and visual/audio properties of a local video asset without modifying it, executing external code, or producing irreversible changes. The analysis capability (extracting technical properties, scene detection, motion, quality metrics) is purely informational with no side effects.
From the tool's definition Tool performs analysis only: 'Analyze one local asset' with 'technical metadata, brightness, saturation, loudness, scenes, semantic frame labels' and explicitly states 'Never identifies a person.' No modification, deletion, execution, or financial operations…
Attacks that exploit this kind of access
The rule that runs analyze_asset_intelligence safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Cutpilot, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For analyze_asset_intelligence, this is the rule to start with:
analyze_asset_intelligence is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Cutpilot, apply this rule, and every analyze_asset_intelligence call is checked against it from then on.
Questions about analyze_asset_intelligence
Analyze one local asset with traceable FFmpeg and optional Apple Vision evidence: technical metadata, brightness, saturation, loudness, scenes, semantic frame labels, non-identity face/person counts, filename/transcript tags, motion and quality. Never identifies a person. It is categorised as a Read tool in the Cutpilot MCP Server, which means it retrieves data without modifying state.
Register the Cutpilot MCP server in PolicyLayer and add a rule for analyze_asset_intelligence: 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 Cutpilot. Nothing to install.
analyze_asset_intelligence is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the analyze_asset_intelligence 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 analyze_asset_intelligence. 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.
analyze_asset_intelligence is provided by the Cutpilot MCP server (Hellotravisss/cutpilot). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Cutpilot, and thousands of servers like it.
This server
Across the catalogue