UE-AUDIO-MCP: Skill for Claude Code

.claude/skills/ue5-audio-mcp/SKILL.md

ue5-audio-mcp is a skill for Claude Code from koshimazaki/UE-AUDIO-MCP. It costs 70 tokens per session (3,484 once invoked), scanned A, original, MIT.

A TCP control interface for an Unreal Engine 5 Editor plugin. TCP is a local network connection; here it lets scripts send JSON commands to build and inspect MetaSounds graphs, which are Unreal’s visual audio-processing networks.

In plain words
What is it for?
Use it to test the connection, create MetaSounds assets, add graph inputs and outputs, scan Blueprints, list project assets, export graphs, and debug the local connection on port 9877.
Why use it?
It removes the need to perform supported audio-editor operations manually when creating graphs, scanning Blueprints, listing assets, or checking the plugin connection.

Skill for Claude Code

Written for Claude Code: allowed-tools in frontmatter.

This is koshimazaki/UE-AUDIO-MCP's own configuration. It tells Claude Code how to work on UE-AUDIO-MCP itself, so it is not a mod to install elsewhere. Copy it as a starting point and replace the rules that are about this project. Everything UE-AUDIO-MCP configures →

Reuse

Borrowing it

Nothing to install: this file belongs to koshimazaki/UE-AUDIO-MCP. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file
curl -O https://raw.githubusercontent.com/koshimazaki/UE-AUDIO-MCP/master/.claude/skills/ue5-audio-mcp/SKILL.md
Clone the repo
git clone --depth 1 https://github.com/koshimazaki/UE-AUDIO-MCP

Made for: Claude Code.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

agentmods badge for ue5-audio-mcp

README.md
[![agentmods](https://agentmods.dev/badge/skills/koshimazaki/ue-audio-mcp/ue5-audio-mcp/github.svg)](https://agentmods.dev/skills/koshimazaki/ue-audio-mcp/ue5-audio-mcp)
Your own site
<a href="https://agentmods.dev/skills/koshimazaki/ue-audio-mcp/ue5-audio-mcp"><img src="https://agentmods.dev/badge/skills/koshimazaki/ue-audio-mcp/ue5-audio-mcp/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

agentmods 80×15 button for ue5-audio-mcp

Your own site · 80×15
<a href="https://agentmods.dev/skills/koshimazaki/ue-audio-mcp/ue5-audio-mcp"><img src="https://agentmods.dev/badge/skills/koshimazaki/ue-audio-mcp/ue5-audio-mcp.svg" alt="Reviewed on agentmods" width="80" height="20"></a>
Per session 70 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 3,484 The whole file, excluding the scripts and references it only reads on demand.
Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.
Origin original No closer match found in the catalogue.
Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

ModelPer sessionOnce invoked
Fable 5.1 $0.00070 $0.03484
Opus 5.5 $0.00028 $0.01394
Sonnet 5.5 $0.00014 $0.00697
Haiku 4.5 $0.00007 $0.00348

Measured 1mo ago against content hash e97d6badf93e, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

ue5-audio-mcp scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 1mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

.claude/skills/ue5-audio-mcp/SKILL.md · 210 lines

How it starts

The opening of the file, as written. The whole thing — 210 lines — stays where its author put it; the contents beside it link to each section on GitHub.

UE Audio MCP Plugin — TCP Control

Drive the C++ TCP server inside Unreal Editor. Each command is flat JSON (action plus its params at the top level), framed with a 4-byte big-endian length prefix, on 127.0.0.1:9877. Commands run on the game thread.

Connection

# Python SDK
from ue_audio_mcp.ue5_connection import get_ue5_connection
conn = get_ue5_connection()
resp = conn.send_command({"action": "ping"})

# Raw TCP
python3 -c "
import socket, struct, json
s = socket.socket(); s.settimeout(5); s.connect(('127.0.0.1', 9877))
p = json.dumps({'action':'ping'}).encode()
s.sendall(struct.pack('>I', len(p)) + p)
r = s.recv(4); l = struct.unpack('>I', r)[0]; print(json.loads(s.recv(l)))
"

Commands

The plugin registers 48 commands. Params marked ? are optional, with defaults in parentheses; every response also carries status (and message on errors). The source of truth is the RegisterCommand calls in ue5_plugin/UEAudioMCP/Source/UEAudioMCP/Private/UEAudioMCPModule.cpp; each command reads its params in Private/Commands/*.cpp.

System

Command Params Returns
ping — engine, version, project, features

Builder lifecycle

Command Params Returns
create_builder asset_type (Source/Patch/Preset), name asset_type, name
add_interface interface —

Graph I/O

Command Params Returns
add_graph_input name, type, default? name, type
add_graph_output name, type name, type

Nodes

Command Params Returns
add_node id, node_type, position? [x,y] id, node_type
set_default node_id, input, value node_id, input
connect from_node, from_pin, to_node, to_pin from_node, from_pin, to_node, to_pin

Build, audition & editor

Command Params Returns
build_to_asset name, path name, path
audition name? —
stop_audition — —
open_in_editor — —

Read the full file on GitHub · 210 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

  1. 1mo ago Changed · +40 lines · +15 tokens per session e97d6badf93e
  2. 2mo ago First seen · 170 lines · 55 tokens per session scan A b9b463c36d2e

Subscribe to this mod's changes

ue5-audio-mcp is a skill published in the GitHub repository koshimazaki/UE-AUDIO-MCP (7 stars, last pushed 1mo ago), licensed MIT. It adds 70 tokens to every session and 3,484 once invoked, about $0.0003 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Related

Other skills, from other repositories

playtest-report

Structured playtest report template, or turn existing playtest notes into structured feedback.

Donchitos/Claude-Code-Game-Studios · 20 tokens

godot-signals-groups

Build event-driven, decoupled Godot 4.7 gameplay with signals and node groups: declare and emit custom signals, connect with Callables (incl. bind/one-shot), and broadcast to many nodes via groups and callgroup. Use when wiring node communication in a Godot project, replacing tight references with signals…

gamedev-skills/awesome-gamedev-agent-skills · 95 tokens

motion

Reconstruct a skeleton from calibrated mesh projections and sequential VLM joint annotations, then fit joints and skin weights. Generate motion from joint-position trajectories, rhythm and contact constraints through IK; refine bone orientation against the action, then export, retarget and validate on the target mesh.

OpenDCAI/GameFactory-3A · 0 tokens

scenario-unreal-gameplay

Use when building or debugging UE5 gameplay: a character with double jump or dash, abilities with cooldowns, enemy AI that patrols, chases and attacks, a health bar or HUD; choosing Blueprint vs C++, GAS or not, StateTree vs Behavior Tree, EQS or Mass; setting up Enhanced Input, Common UI or UMG; replication…

scenario-labs/skills · 121 tokens

unity-addressables

Manage Addressables groups, entries, profiles and content builds (com.unity.addressables, reflection-based).

Besty0728/Unity-Skills · 25 tokens

unity-manual-component

Manually add, configure, reorder, and copy components on GameObjects using Unity Editor UI. For one-off Inspector workflows that do not need REST automation.

Besty0728/Unity-Skills · 36 tokens