Export the transcript of a published project as plain text. Example: export_transcript_txt({ slug:
AI agents call export_transcript_txt to retrieve information from Descript Complete without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves/exports existing transcript data as plain text. It reads from a published project without modifying, deleting, or creating any data. The export is a read operation producing a text representation of existing content.
From the tool's definition Export the transcript of a published project as plain text
Attacks that exploit this kind of access
Export the transcript of a published project as plain text. Example: export_transcript_txt({ slug:. It is categorised as a Read tool in the Descript Complete MCP Server, which means it retrieves data without modifying state.
Register the Descript Complete MCP server in PolicyLayer and add a rule for export_transcript_txt: 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.
export_transcript_txt 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 export_transcript_txt 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 export_transcript_txt. 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.
export_transcript_txt 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 →