// SCAN REPORT

Media-Editor-MCP

47 tools. 27 can modify or destroy data without limits.

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

Last updated: 2 Jul 2026

27 can modify or destroy data

20 read-only

47 tools total

Community server · catalogue entry verified 02/07/2026

How to control Media-Editor-MCP ↓

TOOL MAP

What Media-Editor-MCP exposes to your agents

Read (20) Write / Execute (25) Destructive / Financial (2)

Running more than one server? Check your whole stack →

MOST DANGEROUS TOOLS

Critical Risk

The most dangerous Media-Editor-MCP tools

Destructive · High remove_track_effect This tool irreversibly removes/strips an effect from every clip on an entire video track. Destructive · High remove_clips Removing clips from a video track deletes media elements from the project timeline. Execute · Medium reopen_capcut The tool name implies reopening the CapCut application or a CapCut draft, which would be an external operation/trigger. Write · Medium apply_transition_to_all_cuts This tool creates and modifies project metadata/effects (transitions) across multiple clips in a video editing context.

27 of Media-Editor-MCP's 47 tools can modify, destroy, or commit something on every call — and an agent calls them with no built-in limits.

POLICY

How to control Media-Editor-MCP

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

Deny destructive operations

{
  "remove_clips": {
    "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

{
  "add_animation": {
    "limits": [
      {
        "counter": "add_animation_per_hour",
        "window": "hour",
        "max": 30,
        "scope": "grant"
      }
    ]
  }
}

Prevents bulk unintended modifications from agents caught in loops.

Cap read operations

{
  "analysis_health": {
    "limits": [
      {
        "counter": "analysis_health_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 Media-Editor-MCP — 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 MEDIA-EDITOR-MCP →

Instant setup, no code required.

FULL CATALOGUE

All 47 Media-Editor-MCP tools

DESTRUCTIVE 2 tools

Destructive remove_clips Remove clips by index from a video track. ripple=true closes the gaps. Destructive remove_track_effect Strip an effect (default Lumetri Color) from every clip on a video track — the grade

EXECUTE 1 tools

Execute reopen_capcut reopen_capcut

WRITE 24 tools

Write add_animation Add an in/out/loop animation to a clip. Write add_audio add_audio Write add_captions add_captions Write add_clip_effect add_clip_effect Write add_effect_layer add_effect_layer Write add_filter Apply a color filter to a clip (the CapCut analogue of a Lumetri look/LUT). Write add_filter_layer add_filter_layer Write add_markers Add markers to the active sequence Write add_text add_text Write add_text_block add_text_block Write apply_transition Set the transition that follows a clip (into the next one). Write apply_transition_to_all_cuts Apply a video transition (default: Cross Dissolve) at every cut between adjacent clips Write apply_transition_to_clip Apply a video transition (default: Cross Dissolve) to the start or end edge of a single Write create_draft create_draft Write create_sequence Create a new sequence whose settings match the given media item(s); the items are Write generate_srt Write an .srt subtitle file from transcript segments. Write grade_track Apply one effect (default Lumetri Color) + a set of numeric params to EVERY clip on a Write import_files Import media files (video, audio, images, PNG overlays) into the project root bin. Write place_clip place_clip Write render_text_png Render text to a transparent PNG for use as a Premiere overlay. Write save_draft save_draft Write set_clip_lut DISCOVERY: attempt to set a clip Write set_clip_param Set a fixed numeric value on a placed clip Write transcribe transcribe

READ 20 tools

Read analysis_health Check the analysis server: version, python, which models are loaded. Read cc_health Check the CapCut MCP: version, where it looks for drafts, and the effect catalog size. Read classify_song classify_song Read detect_beats Detect musical beats in an audio (or video) file. Read detect_energy detect_energy Read draft_status Show the active draft's current plan (clips, audio, texts, and their effects). Read fetch_stock_videos fetch_stock_videos Read find_best_moments find_best_moments Read get_audio_clips List clips on audio track(s) with timecodes AND source media file paths — Read get_project_info Get the currently open Premiere Pro project: name, path, and sequence count. Read get_sequence_clips List the clips on a sequence Read list_available_transitions List the video transition matchNames installed in Premiere Pro Read list_drafts List existing CapCut drafts (folder names) in the CapCut drafts directory. Read list_effects list_effects Read list_filters Search just the color filters (shortcut for list_effects with kind='filter'). Read list_project_items List all items in the project bins with type and media file path. Read list_sequences List all sequences in the open Premiere project with their track counts and frame rates. Read premiere_health Check whether the Premiere Pro UXP plugin is connected to this MCP server. Read premiere_ping Round-trip latency/liveness test against the UXP plugin inside Premiere. Read probe_effects Read-only discovery: dumps a clip

EXPLORE

Related servers

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

FAQ

Questions about Media-Editor-MCP

Can an AI agent delete data through the Media-Editor- MCP server? +

Yes. The Media-Editor-MCP server exposes 2 destructive tools including remove_clips, remove_track_effect. 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 Media-Editor-MCP? +

The Media-Editor-MCP server has 24 write tools including add_animation, add_audio, add_captions. 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 Media-Editor-MCP.

How many tools does the Media-Editor- MCP server expose? +

47 tools across 3 categories: Destructive, Read, Write. 20 are read-only. 27 can modify, create, or delete data.

How do I enforce a policy on Media-Editor-MCP? +

Register the Media-Editor- 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 Media-Editor-MCP tool call.

Deterministic rules across all 47 Media-Editor-MCP tools. Per-identity grants. Full audit log. Live in minutes. Nothing to install.

ENFORCE POLICY ON MEDIA-EDITOR-MCP →

Instant setup, no code required.

47 Media-Editor-MCP tools catalogued and risk-classified — across an index of 43,000+ MCP servers.