analyze_project_assets
Batch-analyze online video, audio, and image assets locally with FFmpeg and optional Apple Vision semantics, returning a reviewable evidence bundle without mutating the project.
This record as markdown: /tools/cutpilot/analyze-project-assets.md
What analyze_project_assets does on Cutpilot
AI agents call analyze_project_assets 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_project_assets is rated Low
This tool retrieves and analyzes media asset data (video, audio, image metadata and semantic information) using FFmpeg and optional vision processing. It produces analysis output for review but does not create, modify, delete, or execute arbitrary code—it only reads and processes existing assets locally. This is a classic Read category operation with minimal blast radius.
From the tool's definition Tool description states it performs 'analyze' operations that return 'a reviewable evidence bundle without mutating the project.' The phrase 'without mutating' explicitly confirms no side effects or modifications occur.
Attacks that exploit this kind of access
The rule that runs analyze_project_assets 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_project_assets, this is the rule to start with:
analyze_project_assets 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_project_assets call is checked against it from then on.
Questions about analyze_project_assets
Batch-analyze online video, audio, and image assets locally with FFmpeg and optional Apple Vision semantics, returning a reviewable evidence bundle without mutating the project. 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_project_assets: 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_project_assets 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_project_assets 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_project_assets. 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_project_assets 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