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 55 tokens per session (2,092 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 55 Skills are progressive disclosure: only the name and description are preloaded; the body loads when the skill is used.
When invoked 2,092 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 $0.00055 $0.02092
Opus 5 $0.00028 $0.01046
Sonnet 5 $0.00011 $0.00418
Haiku 4.5 $0.00006 $0.00209

Measured 12d ago against content hash b9b463c36d2e, method: parsed. Prices are Anthropic first-party input rates as of 2026-09-11, 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 12d 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 · 170 lines

How it starts

The opening of the file, as written. The whole thing — 170 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. All commands use 4-byte big-endian length prefix + UTF-8 JSON on 127.0.0.1:9877.

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)))
"

All 25 Commands

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
build_to_asset name, path (/Game/...) name, path

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 all four

__graph__ = sentinel node ID for graph boundary connections.

Audition

Command Params Returns
audition name?
stop_audition
open_in_editor

Variables (UE 5.7+)

Command Params Returns
add_graph_variable name, type, default? name, type
add_variable_get_node id, variable_name, delayed? id, variable_name
add_variable_set_node id, variable_name id, variable_name

Presets

Command Params Returns
convert_to_preset referenced_asset (/Game/...) referenced_asset
convert_from_preset

Read the full file on GitHub · 170 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. 12d 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 (5 stars, last pushed 2mo ago), licensed MIT. It adds 55 tokens to every session and 2,092 once invoked, about $0.0003 per session on Opus 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

gameobject-component-destroy

Destroy one or more Components from a target GameObject. Missing (null) components are skipped — they cannot be destroyed. Use 'gameobject-find' and 'gameobject-component-get' to identify the components first.

IvanMurzak/Unity-MCP · 49 tokens

unity-version-split

Split a C# file into Unity 6.5+ and pre-Unity 6.5 variants. Use when a file needs different implementations for different Unity versions due to API changes (e.g., EntityId vs int, GetEntityId vs GetInstanceID).

IvanMurzak/Unity-MCP · 59 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

unity-addressables

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

Besty0728/Unity-Skills · 25 tokens

motion

How an agent turns a character mesh into a usable animated FBX — and how to judge whether the result is shippable.

OpenDCAI/GameFactory-3A · 0 tokens

threejs-exposure-color-grading

Build a measured exposure and grading path in Three.js. Use for a 64x36 encoded luminance meter, asynchronous readback, weighted log-average exposure, asymmetric adaptation, single tone-map ownership, and a generated 32-cube post-tone-map LUT.

scottstts/Threejs-Awesome-Graphics-Agent-Skills · 60 tokens