capcut-mcp

Overview Schema Source Related Servers Discussions Admin

capcut_duck_music

Read SRT cues to lower music volume under speech in CapCut drafts, writing volume keyframes per segment. Dry-run by default.

Instructions

Lower the music under speech: reads SRT cues and writes volume keyframes on every segment of the music track (under = level during speech, free = level between lines, default the segment volume). Dry-run by default.

Tool call template

Replace each placeholder with a value matching the input schema. Only required parameters are included; add optional parameters as needed.

{
  "id": 1,
  "jsonrpc": "2.0",
  "method": "tools/call",
  "params": {
    "arguments": {
      "draft": "<draft>"
    },
    "name": "capcut_duck_music"
  }
}

Input Schema

Name	Required	Description	Default
`free`	No
`draft`	Yes	Draft folder name inside the drafts root (from capcut_list_drafts).
`track`	No		music
`under`	No
`ramp_s`	No
`dry_run`	No	true (default): return the plan only. false: write to disk (CapCut must be closed).
`offset_s`	No	Shift every cue (same as add_subtitles offset_s).
`srt_path`	No	Absolute path of the voice .srt.
`srt_text`	No
`merge_gap_s`	No	Pauses shorter than this stay ducked.

Schema Changelog

Changes observed during successful MCP inspections.

First observedv0.3.0Oct 15, 2026

TDQS

A3.8/5.0

Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

With no annotations, the description carries the load and does well: it discloses that it writes keyframes on disk, that dry-run is the default, and clarifies the under/free semantics. It omits prerequisites such as CapCut being closed and permission requirements, which the schema only partially covers.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

A single dense, front-loaded sentence with a clarifying parenthetical; the core action leads and details follow. No wasted words, though the nested parenthetical is slightly crowded.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness3/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

For a 10-parameter, no-annotation, no-output-schema mutation tool, the description covers the core behavior and two key params but is silent on return/plan format and several parameters (ramp_s, merge_gap_s). Sufficient to start but not fully complete.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 50%, so the description needs to compensate. It usefully explains 'under' (level during speech), 'free' (level between lines), and the default segment volume, but ramp_s, merge_gap_s, and track behavior are left to the schema, so it only partially closes the gap.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

States a specific verb+resource (lower music under speech) and the exact mechanism (reads SRT cues, writes volume keyframes on the music track). This is clearly distinct from generic siblings like capcut_add_keyframes or capcut_add_audio, so an agent can select it without opening the schema.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines3/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

The scenario is implied by 'under speech' and 'reads SRT cues', so an agent can infer when it applies, but there is no explicit when-to-use/when-not guidance and no named alternative (e.g. vs. capcut_add_keyframes). Adequate but leaves routing to inference.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.