MCP Flux Studio
MCP Flux Studio integrates Flux's image generation and manipulation capabilities into AI coding assistants.
Image Generation: Generate images from text prompts with multiple models, customizable aspect ratios, and dimensions.
Image Manipulation: Transform images using reference images (img2img), inpaint specific areas with masks, and upscale resolution.
Advanced Controls: Generate images using structural controls like edges (canny), depth, or pose guidance.
IDE Integration: Seamlessly integrate with Cursor and Windsurf/Codeium IDEs for AI-assisted tool invocation.
Customization: Configure generation settings including model, strength, and dimensions for precise outputs.
Automation: Streamline development workflows through CLI tools and IDE integrations.
Integrates with Windsurf/Codeium Cascade (Wave 3+), allowing users to access image generation tools through Cascade's MCP toolbar and AI capabilities
Integrates with Flux's image generation API, allowing for text-to-image generation, image-to-image transformation, inpainting, and advanced image controls like edge-based, depth-aware, and pose-guided generation
Click on "Deploy 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., "@MCP Flux Studio generate a minimalist logo design for a tech startup called 'Nexus'"
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.
mcp-flux-studio
MCP server that wraps the Flux image generation API. Exposes text-to-image, image-to-image, inpainting, and structural control (canny/depth/pose) as MCP tools over stdio. The server itself is TypeScript; it shells out to a Python CLI (fluxcli.py) for actual API calls.
What It Does
Receives MCP tool calls, builds command-line arguments, spawns python3 fluxcli.py <subcommand> ... against a local Flux installation, and returns the output. Requires a BFL_API_KEY for the Flux API and a local copy of the Flux CLI.
Related MCP server: Flux Schnell MCP Server
Status
Area | State |
MCP transport | stdio |
Language | TypeScript (server) + Python (CLI wrapper) |
Flux models | flux.1.1-pro, flux.1-pro, flux.1-dev, flux.1.1-ultra |
Tests | Jest, 2 test files |
IDE tested | Cursor v0.45.7+, Windsurf/Codeium Wave 3+ |
npm package |
|
License | MIT |
MCP Tools
Tool | Required Params | Optional Params | Output |
|
|
| Generated image path |
|
|
| Transformed image path |
|
|
| Inpainted image path |
|
|
| Controlled image path |
Width and height are validated to 256-2048 range.
Setup
Via Smithery
npx -y @smithery/cli install @jmanhype/mcp-flux-studio --client claudeManual
git clone https://github.com/jmanhype/mcp-flux-studio.git
cd mcp-flux-studio
npm install
npm run build
npm startEnvironment Variables
Variable | Required | Description |
| Yes | Flux API key |
| No | Path to Flux CLI installation (default: |
| No | If set, uses |
IDE Configuration
Cursor: Settings > Features > MCP. Supports stdio and SSE.
Windsurf/Codeium: Edit ~/.codeium/windsurf/mcp_config.json.
Architecture
src/
index.ts — MCP server, tool handlers, Python process spawning
types.ts — TypeScript interfaces for tool arguments
cli/
fluxcli.py — Python CLI that calls the Flux API (not in this repo's src)
tests/
server.test.ts
types.test.tsLimitations
Shells out to Python for every tool call; each call spawns a new process
The default
FLUX_PATHis hardcoded to a local directoryNo connection pooling or request queuing for the Flux API
No image previews returned in MCP responses — only file paths
The
ControlTypetype is referenced but not imported inindex.tsNo progress reporting during generation
Dependencies
Package | Version | Purpose |
| ^0.1.0 | MCP server protocol |
| ^16.0.3 | Environment variable loading |
| ^5.0.3 | Build toolchain |
| ^29.5.0 | Test runner |
License
MIT
Available Tools
4 toolscontrolC
Generate an image using structural control
Inputs: type (required), image (required), prompt (required), steps, +2 more.
generateC
Generate an image from a text prompt
Inputs: prompt (required), model, aspect_ratio, width, +2 more.
img2imgC
Generate an image using another image as reference
Inputs: image (required), prompt (required), name (required), model, +4 more.
inpaintC
Inpaint an image using a mask
Inputs: image (required), prompt (required), mask_shape, position, +1 more.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelog…
TDQS
Scored across 4 tools
Each tool has a clearly distinct purpose with no overlap: 'control' uses structural guidance, 'generate' creates from text, 'img2img' references an image, and 'inpaint' modifies with a mask. The descriptions make it easy to differentiate between structural generation, text-to-image, image-to-image, and inpainting workflows.
The naming is mixed: 'control' and 'generate' are verbs only, while 'img2img' and 'inpaint' are compound terms. There's no consistent pattern like verb_noun, but the names are still readable and descriptive of their functions, avoiding chaotic conventions.
With 4 tools, this is well-scoped for an image generation server. Each tool earns its place by covering distinct aspects of image creation and manipulation, providing a focused set without being too thin or overwhelming for the domain.
The toolset covers core image generation workflows: text-to-image, image-to-image, inpainting, and controlled generation. A minor gap might be the lack of tools for post-processing or batch operations, but the essential CRUD-like operations for image creation are well-represented.
Maintenance
Related MCP Connectors
MCP server for Flux AI image generation
Official FLUX MCP server. Generate, edit, vary, and browse images from Black Forest Labs.
Image and video AI tools and your own pipelines, run from any AI assistant.
Generate images from Claude, ChatGPT, Cursor and Codex with 12 top AI image models. Up to 4 images per call, SVG vectorization, background removal, upscaling and image-to-video. Remote MCP with OAuth, no API keys.
Related MCP Servers
- AlicenseBqualityBmaintenanceA Model Context Protocol server that enables high-quality image generation using the Flux.1 Schnell model via Together AI with customizable parameters.1304 npm10MIT
- AlicenseNot gradedqualityDmaintenanceA server that enables generating images through the Replicate API by calling the Flux Schnell model via the Model Context Protocol (MCP).2MIT
- AlicenseBqualityDmaintenanceAn MCP server that enables AI assistants to generate images using Black Forest Labs' Flux model via Cloudflare Workers.1MIT
- AlicenseAqualityBmaintenanceAI image generation with 6 Flux models (flux-dev, flux-pro, flux-kontext) including context-aware image editing, async task management, and built-in model guide.7440 PyPI3MIT