plan_talking_head_director
Create a non-mutating talking-head plan from a transcribed camera source: remove only standalone filler cues, preserve reviewable source segments, semantically match B-roll, and propose a voice chain.
This record as markdown: /tools/cutpilot/plan-talking-head-director.md
What plan_talking_head_director does on Cutpilot
AI agents use plan_talking_head_director to create or update resources in Cutpilot, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Cutpilot environment.
Why plan_talking_head_director is rated Medium
This tool generates new structured planning data (a talking-head director plan with B-roll matching and voice chain suggestions) that will typically be persisted and used to guide video editing operations. While it does not directly execute edits, it creates and returns new editable/executable artifacts.
From the tool's definition Tool creates a 'plan' that involves semantic matching, voice chain proposal, and segment preservation decisions.
Attacks that exploit this kind of access
The rule that runs plan_talking_head_director 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 plan_talking_head_director, this is the rule to start with:
plan_talking_head_director stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. 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 plan_talking_head_director call is checked against it from then on.
Questions about plan_talking_head_director
Create a non-mutating talking-head plan from a transcribed camera source: remove only standalone filler cues, preserve reviewable source segments, semantically match B-roll, and propose a voice chain. It is categorised as a Write tool in the Cutpilot MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Cutpilot MCP server in PolicyLayer and add a rule for plan_talking_head_director: 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.
plan_talking_head_director is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the plan_talking_head_director 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 plan_talking_head_director. 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.
plan_talking_head_director 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