rank_assets_for_narration
Rank annotated footage for a narration phrase while penalizing repeated shots.
This record as markdown: /tools/cutpilot/rank-assets-for-narration.md
What rank_assets_for_narration does on Cutpilot
AI agents call rank_assets_for_narration 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 rank_assets_for_narration is rated Low
The tool performs an analytical ranking operation on existing footage metadata. It reads annotations and computes a ranked order based on a narration phrase, with a penalty heuristic for repeated shots. There are no side effects: no data is created, modified, deleted, or executed. This is a pure query/analysis operation, consistent with the other 'analyze_*' sibling tools on this server.
From the tool's definition "Rank annotated footage for a narration phrase while penalizing repeated shots" — this is a ranking/scoring operation that reads and evaluates existing annotated footage without modifying or deleting anything.
Attacks that exploit this kind of access
The rule that runs rank_assets_for_narration 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 rank_assets_for_narration, this is the rule to start with:
rank_assets_for_narration 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 rank_assets_for_narration call is checked against it from then on.
Questions about rank_assets_for_narration
Rank annotated footage for a narration phrase while penalizing repeated shots. 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 rank_assets_for_narration: 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.
rank_assets_for_narration 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 rank_assets_for_narration 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 rank_assets_for_narration. 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.
rank_assets_for_narration 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