@lweight/xbrush-api-mcp
Provides text-to-speech and sound effect generation using ElevenLabs models, enabling natural voice synthesis and audio effects.
Provides access to OpenAI models for image generation (e.g., gpt-image-2) and chat completions via an OpenAI-compatible API.
Click on "Install Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@@lweight/xbrush-api-mcpGenerate an image of a cat sitting on a desk"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
@lweight/xbrush-api-mcp
MCP server for the XBrush AI media generation API — images, video, speech, music, sound effects, lip-sync (incl. talking photos), video extend/retake, LLM chat, content moderation, and watermarks, directly from Claude Code.
Quick Start
1. Get an API Key
Get your key at xbrush.run/api-keys.
2. Configure Claude Code
Add to your MCP settings:
{
"mcpServers": {
"xbrush": {
"command": "npx",
"args": ["-y", "@lweight/xbrush-api-mcp"],
"env": {
"XBRUSH_API_KEY": "your_api_key_here"
}
}
}
}3. Use It
"Generate an image of a cat sitting on a desk"
"Remove the background from this image"
"Read this script aloud in Korean"
"Create a 30-second upbeat synth track"
"Extend this video by another 5 seconds"
"Make this portrait photo say the following line"
"Ask GLM 5.2 to summarize this paragraph"Related MCP server: mcp-fal
How results work
All generation tools submit asynchronously and return a request_id. Poll it with
xbrush_get_request until status is completed, then read the output URL(s).
The blocking /sync endpoints are intentionally never called (see CLAUDE.md).
The one exception is xbrush_chat (LLM chat completions): it is synchronous and returns
the completion text directly — the API has no async variant for it. Responses must fit the
platform's ~30s gateway limit; if a 504 cuts the connection, the request keeps processing
server-side and its result can be recovered via xbrush_list_requests + xbrush_get_request.
Available Tools (21)
Image (4)
Tool | Description |
| Generate images from text (e.g. seedream-5.0-pro, nano-banana-pro, flux.2-pro, gpt-image-2, z-image-turbo) |
| Edit / inpaint (qwen-image-edit, seedream-5.0-pro-edit, flux.2-pro-edit) or outpaint (flux-outpaint, qwen-outpaint) |
| Upscale images (2x / 4x) |
| Remove background |
Video (5)
Tool | Description |
| Image-/text-/reference-to-video (e.g. kling-v3/o3, veo3.1, seedance-2.0, hailuo-02, wan-2.7). seedance-2.0 supports multi-reference via |
| Upscale videos (realesrgan, seedvr) |
| Lip-sync a face video (pixverse-lipsync, infinite-talk) or animate a still portrait as a talking photo (fabric-1.0) — speech from audio or built-in TTS ( |
| Extend an existing video by 1–20 seconds |
| Regenerate a video variation up to a timestamp |
Audio (3)
Tool | Description |
| Text-to-speech (e.g. speech-2.8-hd, eleven-v3) |
| Music generation from text (lyria2, lyria3, lyria3-pro) |
| Generate sound effects for a video — video-driven (pixverse) or prompt-driven (elevenlabs, stable-audio) |
Text (1)
Tool | Description |
| LLM chat completions (e.g. GLM 5.2) — synchronous, OpenAI-compatible, billed per token |
Utility (8)
Tool | Description |
| NSFW moderation + masking for an image or video |
| Add the XBrush watermark to an image/video |
| List available AI models with pricing, vendor, and per-model duration constraints |
| List TTS voices (use a |
| Check status/result of an async operation |
| List recent API requests |
| Upload a local file to the XBrush CDN (auto / direct / presign) |
| Check API server status |
Environment Variables
Variable | Required | Description |
| Yes | Your XBrush API key |
| No | API base URL. Defaults to |
| No | Comma-separated tool names to skip. Safety valve for selectively disabling a specific tool without uninstalling. Example: |
License
MIT
Maintenance
Resources
Unclaimed servers have limited discoverability.
Looking for Admin?
If you are the server author, to access and configure the admin panel.
Related MCP Servers
- Alicense-qualityAmaintenanceMCP server that bridges ChatGPT Plus/Pro to Claude Code, enabling chat, deep research, and image generation via your own account.Last updated46MIT
- FlicenseAqualityBmaintenanceAn MCP server that exposes Fal.ai generative media models as tools for image and video generation, and running any Fal.ai model, callable by Claude and other MCP-compatible clients.Last updated3
- AlicenseAqualityBmaintenanceMCP server for AI-powered image, audio, and video generation, enabling media creation directly from Claude, Cursor, and other MCP clients.Last updated1151MIT
- AlicenseAqualityDmaintenanceMCP server for xmorf API enabling AI image editing and generation via natural language prompts.Last updated357MIT
Related MCP Connectors
MCP server for Hailuo (MiniMax) AI video generation
MCP server for Grok Imagine AI video generation
MCP server for Kling AI video generation
Latest Blog Posts
- Who's Calling? MCP Hosts Are an Identity Blind Spot (And the Spec Knows It)By Om-Shree-0709 on .mcpAgent IdentityOAuth 2.1
- Your AI Chatbot Just Exposed Your CEO's Salary to an InternBy Om-Shree-0709 on .Agent IdentityMCP SecurityOAuth Delegation
- Why MCP Servers Need Execution Sandboxing (And Why Your Current Stack Isn't Enough)By Om-Shree-0709 on .Agentic AiPrompt InjectionWebAssembly
MCP directory API
We provide all the information about MCP servers via our MCP API.
curl -X GET 'https://glama.ai/api/mcp/v1/servers/lweight/xbrush-api-mcp'
If you have feedback or need assistance with the MCP directory API, please join our Discord server