What is xbrush-api-mcp CLAUDE.md?

A project guide for an MCP server that connects coding agents to XBrush, an AI service for creating media. It describes the project, its structure, requirements, and development practices.

It helps with developing the XBrush MCP server, including its tools, input checks, file uploads, API requests, and error handling.

It gives an agent the project-specific context needed to work consistently on the server instead of guessing how the code is organized.

How lweight/xbrush-api-mcp configures Claude Code

Reuse

Borrowing it

Nothing to install: this file belongs to lweight/xbrush-api-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/lweight/xbrush-api-mcp/main/CLAUDE.md

Clone the repo

git clone --depth 1 https://github.com/lweight/xbrush-api-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.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/lweight/xbrush-api-mcp/claude-md/github.svg)](https://agentmods.dev/instructions/lweight/xbrush-api-mcp/claude-md)

Your own site

<a href="https://agentmods.dev/instructions/lweight/xbrush-api-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lweight/xbrush-api-mcp/claude-md/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.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/lweight/xbrush-api-mcp/claude-md"><img src="https://agentmods.dev/badge/instructions/lweight/xbrush-api-mcp/claude-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 9,975 This file is loaded in full into every session.

When invoked 9,975 The same file — it is already loaded in full.

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.

Model	Per session	Once invoked
Fable 5.1	$0.09975	$0.09975
Opus 5.5	$0.03990	$0.03990
Sonnet 5.5	$0.01995	$0.01995
Haiku 4.5	$0.00997	$0.00997

Measured 2mo ago against content hash 35881a09bf08, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

xbrush-api-mcp CLAUDE.md 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 2mo 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.md · 208 lines

How it starts

The opening of the file, as written. The whole thing — 208 lines — stays where its author put it; the contents beside it link to each section on GitHub.

@lweight/xbrush-api-mcp

프로젝트 개요

목적: XBrush AI 미디어 생성 API용 MCP 서버
회사: 라이트웨이트(주) (Lightweight Inc.)
npm: @lweight/xbrush-api-mcp (public, MIT)
GitHub: lweight/xbrush-api-mcp

구조

src/
├── index.ts              ← 서버 엔트리, 13개 도구 모듈 등록 (37 tools)
├── constants.ts          ← API 베이스 URL, 타임아웃 상수, 응답 크기 한도
├── types.ts              ← 공통 타입 정의 (output 형태·모델 constraints·동기 유틸 응답)
├── tool-filter.ts        ← XBRUSH_DISABLED_TOOLS 환경변수 처리
├── schemas/              ← Zod 입력 스키마
│   ├── audio.ts          ← tts(+timestamps) / music / sound-effect / stt
│   ├── chat.ts           ← chat completions (LLM) — response_format 포함
│   ├── file-upload.ts
│   ├── image.ts          ← generate/edit/upscale/remove-bg/outpaint/inpaint/enhance/layer-split + segment-detect/vision/product-lookup
│   ├── lip-sync.ts       ← 영상/사진(talking photo) lip-sync
│   ├── lora.ts           ← lora_train (LoRA 학습)
│   ├── media.ts          ← media ffmpeg / image-process / graph / info
│   ├── models.ts
│   ├── moderation.ts     ← content_moderate (image/video, threshold)
│   ├── requests.ts       ← get/list(domain·action·status 필터)
│   ├── video.ts          ← generate / upscale / extend / retake / edit / vision
│   ├── voice.ts          ← list_voices(+voice_id 상세) / voice_clone
│   └── watermark.ts      ← strength
├── services/
│   ├── dispatch.ts       ← submitAsync(async 단일 경로) + callSync(동기 유틸 전용)
│   ├── file-upload.ts    ← 파일 업로드 (presign / direct / auto) + MIME 맵
│   └── xbrush-client.ts  ← HTTP 클라이언트 + 에러 매핑 + 기본 포맷터
└── tools/                ← MCP 도구 핸들러
    ├── audio.ts          ← tts_generate(with_timestamps→/v1/tts-wt), music_generate, sound_effect_generate, stt_transcribe
    ├── chat.ts           ← xbrush_chat (동기 LLM)
    ├── file-upload.ts    ← xbrush_file_upload
    ├── image.ts          ← generate, edit, upscale, remove_bg, outpaint, inpaint, enhance, layer_split (async) + segment_detect, vision, product_lookup (동기)
    ├── lip-sync.ts       ← xbrush_video_lip_sync
    ├── lora.ts           ← xbrush_lora_train
    ├── media.ts          ← media_ffmpeg, media_image_process, media_graph (async) + media_info (동기, 무료)
    ├── models.ts         ← xbrush_list_models
    ├── moderation.ts     ← xbrush_content_moderate
    ├── requests.ts       ← get_request(범용 output 렌더), list_requests(필터), check_health
    ├── video.ts          ← video_generate, video_upscale, video_extend, video_retake, video_edit, video_vision
    ├── voice.ts          ← xbrush_list_voices, xbrush_voice_clone (동기)
    └── watermark.ts      ← xbrush_watermark_add

Read the full file on GitHub · 208 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.

2mo ago Changed · +40 lines · +4,026 tokens per session 35881a09bf08
2mo ago First seen · 168 lines · 5,949 tokens per session scan A 7f5eb9dc9955

Subscribe to this mod's changes

xbrush-api-mcp CLAUDE.md is an instructions file published in the GitHub repository lweight/xbrush-api-mcp (0 stars, last pushed 2mo ago), licensed MIT. It adds 9,975 tokens to every session, about $0.0399 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.

xbrush-api-mcp CLAUDE.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
xbrush-api-mcp CLAUDE.mdlweight/xbrush-api-mcp	Instructions file	0	2mo ago	MIT	A	9,975	Claude Code
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

xbrush-api-mcp: Instructions file for Claude Code