// SCAN REPORT

Descript Complete

20 tools. 10 can modify or destroy data without limits.

2 destructive tools with no built-in limits. Policy required.

Last updated: 3 Jul 2026

10 can modify or destroy data

10 read-only

20 tools total

Community server · catalogue entry verified 03/07/2026

How to control Descript Complete ↓

TOOL MAP

What Descript Complete exposes to your agents

Read (10) Write / Execute (8) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Descript Complete tools

Destructive · High delete_project This tool permanently deletes a Descript project, which cannot be undone. Destructive · High remove_filler_words Use the Descript AI agent to remove filler words (um, uh, like, you know) from a project transcript. Example: remove_filler_words({ project_ Execute · Medium remove_silence This tool triggers an AI agent to perform automated audio/video editing (removing silence) on a project. Execute · High create_overdub This tool executes an AI voice synthesis operation that replaces or regenerates speech in a project.

10 of Descript Complete's 20 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Descript Complete

PolicyLayer is an MCP gateway — it sits between your AI agents and Descript Complete, and nothing reaches the server without passing your rules. These are the rules we recommend:

Deny destructive operations

{
  "delete_project": {
    "deny_if": [
      {
        "conditions": [],
        "on_deny": "Blocked by default. Requires approval."
      }
    ]
  }
}

Destructive tools should never be available to autonomous agents without human approval.

Rate limit write operations

{
  "create_project": {
    "limits": [
      {
        "counter": "create_project_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "export_transcript_srt": {
    "limits": [
      {
        "counter": "export_transcript_srt_per_minute",
        "window": "minute",
        "max": 60,
        "scope": "grant"
      }
    ]
  }
}

Controls API costs and prevents retry loops from exhausting upstream rate limits.

Create a free account and register Descript Complete — nothing to install.
Add these rules — paste them, or build them visually. Tune the limits to your setup.
Point your MCP client (Claude, Cursor, anything) at your gateway URL.

ENFORCE POLICY ON DESCRIPT COMPLETE →

Instant setup, no code required.

FULL CATALOGUE

All 20 Descript Complete tools

DESTRUCTIVE 2 tools

Destructive delete_project Delete a Descript project permanently. Example: delete_project({ project_id: Destructive remove_filler_words Use the Descript AI agent to remove filler words (um, uh, like, you know) from a project transcript. Example:

EXECUTE 4 tools

Execute create_overdub Use Descript Overdub to regenerate or replace speech in a project using AI voice. Example: create_overdub({ pr Execute export_video Use the Descript agent to export/render the video for a project. Example: export_video({ project_id: Execute remove_silence Use the Descript AI agent to remove silent gaps from a project. Example: remove_silence({ project_id: Execute transcribe_audio Submit an audio file URL for transcription. Returns a job ID to poll with get_transcript. Example: transcribe_

WRITE 4 tools

Write create_project Create a new Descript project. Example: create_project({ name: Write share_project Share a Descript project with a collaborator by email. Example: share_project({ project_id: Write trim_transcript Use the Descript AI agent to trim or edit content in a project based on a prompt. Example: trim_transcript({ p Write upload_media Upload media to a Descript project via URL. Example: upload_media({ project_id:

READ 10 tools

Read export_transcript_srt Export the transcript of a published project in SRT subtitle format. Example: export_transcript_srt({ slug: Read export_transcript_txt Export the transcript of a published project as plain text. Example: export_transcript_txt({ slug: Read get_project Get details for a specific Descript project. Example: get_project({ project_id: Read get_project_members Get the list of collaborators on a Descript project. Example: get_project_members({ project_id: Read get_transcript Fetch the transcript for a published Descript project by its share slug. Example: get_transcript({ slug: Read get_upload_status Check the status of a media upload or processing job. Example: get_upload_status({ job_id: Read list_overdub_voices List available Overdub AI voices for your account. Example: list_overdub_voices({}) Read list_projects List all Descript projects in your account. Example: list_projects({ limit: 20 }) Read list_transcripts List recent transcription jobs. Example: list_transcripts({ limit: 5 }) Read transcribe_video Submit a video file URL for transcription. Returns a job ID to poll with get_transcript. Example: transcribe_v

EXPLORE

Related servers

Other MCP servers with similar tools — same risk classification, starter policies for each.

FAQ

Questions about Descript Complete

Can an AI agent delete data through the Descript Complete MCP server? +

Yes. The Descript Complete server exposes 2 destructive tools including delete_project, remove_filler_words. These permanently remove resources with no undo. PolicyLayer blocks destructive tools by default so they never reach the upstream server.

How do I prevent bulk modifications through Descript Complete? +

The Descript Complete server has 4 write tools including create_project, share_project, trim_transcript. Set a rate limit in your policy -- for example, 10 calls per hour prevents an agent from making more than 10 modifications per hour. PolicyLayer enforces this at the gateway, before calls reach Descript Complete.

How many tools does the Descript Complete MCP server expose? +

20 tools across 3 categories: Destructive, Read, Write. 10 are read-only. 10 can modify, create, or delete data.

How do I enforce a policy on Descript Complete? +

Register the Descript Complete MCP server in PolicyLayer, apply the suggested rules above (adjust the limits to your use case), and point your AI client at the PolicyLayer proxy URL instead of the server directly. Your agents keep the same tools; PolicyLayer evaluates every call against policy before it executes. Nothing to install, live in minutes.

Enforce policy on every Descript Complete tool call.

Deterministic rules across all 20 Descript Complete tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON DESCRIPT COMPLETE →

Instant setup, no code required.

20 Descript Complete tools catalogued and risk-classified — across an index of 43,000+ MCP servers.