trim_transcript · Descript Complete MCP: Risk & Policy

WHAT IT DOES

What trim_transcript does on Descript Complete

AI agents use trim_transcript to create or update resources in Descript Complete — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Descript Complete environment.

WHY IT NEEDS A POLICY

Why trim_transcript needs a policy

This tool modifies transcript content reversibly (trim/edit operations can typically be undone in Descript). It is a Write operation because it creates or modifies data without irreversibly destroying it. Severity is medium because transcript modifications could impact project integrity or collaboration, but the effects are reversible.

From the tool's definition Tool is named 'trim_transcript' with description stating it will 'trim or edit content in a project based on a prompt.' The verb 'trim' and 'edit' indicate modification of existing transcript data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

trim_transcript Rate-limited

trim_transcript 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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "trim_transcript": {
      "limits": [
        {
          "counter": "trim_transcript_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Descript Complete, so you can run agents against it safely.

FAQ

Questions about trim_transcript

What does the trim_transcript tool do? +

Use the Descript AI agent to trim or edit content in a project based on a prompt. Example: trim_transcript({ project_id:. It is categorised as a Write tool in the Descript Complete MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on trim_transcript? +

Register the Descript Complete MCP server in PolicyLayer and add a rule for trim_transcript: 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.

What risk level is trim_transcript? +

trim_transcript is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit trim_transcript? +

Yes. Add a rate_limit block to the trim_transcript 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.

How do I block trim_transcript completely? +

Set action: deny in the PolicyLayer policy for trim_transcript. 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.

What MCP server provides trim_transcript? +

trim_transcript 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.