Use the Descript AI agent to remove filler words (um, uh, like, you know) from a project transcript. Example: remove_filler_words({ project_id:
AI agents call remove_filler_words to permanently remove resources in Descript Complete — typically in cleanup and lifecycle workflows. It does its job in a single call, and there is no undo.
An AI agent that decides to call remove_filler_words doesn't hesitate, doesn't double-check, and doesn't stop at one. Whatever it removes from Descript Complete is gone — there is no undo for destructive operations.
Attacks that exploit this kind of access
Use the Descript AI agent to remove filler words (um, uh, like, you know) from a project transcript. Example: remove_filler_words({ project_id:. It is categorised as a Destructive tool in the Descript Complete MCP Server, which means it can permanently delete or destroy data. Block by default and require explicit approval.
Register the Descript Complete MCP server in PolicyLayer and add a rule for remove_filler_words: 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 Descript Complete. Nothing to install.
remove_filler_words is a Destructive tool with critical risk. Critical-risk tools should be blocked by default and only enabled with explicit human approval.
Yes. Add a rate_limit block to the remove_filler_words 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 remove_filler_words. 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.
remove_filler_words is provided by the Descript Complete MCP server (josephtandle/descript-complete). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →