Skip to main content
Glama
README.md
# mcp-flux-schnell MCP Server

[![smithery badge](https://smithery.ai/badge/@bytefer/mcp-flux-schnell)](https://smithery.ai/server/@bytefer/mcp-flux-schnell)

A TypeScript-based MCP server that implements a text-to-image generation tool using the Flux Schnell model. This server integrates with Cloudflare's Flux Schnell worker API to provide image generation capabilities through MCP.

- [Creating your own Flux Schnell MCP Server is so easy! — Part 1](https://medium.com/@bytefer/creating-your-own-flux-schnell-mcp-server-is-so-easy-part-1-4b9a5b3fb14f)
- [Creating your own Flux Schnell MCP Server is so easy! — Part 2](https://medium.com/@bytefer/creating-your-own-flux-schnell-mcp-server-is-so-easy-part-2-bd711836a493)

## Features

### Tools
- `generate_image` - Generate images from text descriptions
  - Takes a text prompt as input (1-2048 characters)
  - Returns the path to the generated image file

## Environment Variables

The following environment variables must be configured:

- `FLUX_API_URL` - The URL of the Flux Schnell API endpoint
- `FLUX_API_TOKEN` - Your authentication token for the Flux Schnell API
- `WORKING_DIR` (optional) - Directory where generated images will be saved (defaults to current working directory)

## Development

Install dependencies:
```bash
npm install
# or
pnpm install
```

Build the server:
```bash
npm run build
# or
pnpm build
```

## Installation

### Installing via Smithery

To install Flux Schnell Image Generator for Claude Desktop automatically via [Smithery](https://smithery.ai/server/@bytefer/mcp-flux-schnell):

```bash
npx -y @smithery/cli install @bytefer/mcp-flux-schnell --client claude
```

### Cursor Configuration

There are two ways to configure the MCP server in Cursor:

#### Project Configuration

For tools specific to a project, create a `.cursor/mcp.json` file in your project directory:

```json
{
  "mcpServers": {
    "mcp-flux-schnell": {
      "command": "node",
      "args": ["/path/to/mcp-flux-schnell/build/index.js"],
      "env": {
        "FLUX_API_URL": "your flux api url",
        "FLUX_API_TOKEN": "your flux api token",
        "WORKING_DIR": "your working directory"
      }
    }
  }
}
```

This configuration will only be available within the specific project.

#### Global Configuration

For tools that you want to use across all projects, create a `~/.cursor/mcp.json` file in your home directory with the same configuration:

```json
{
  "mcpServers": {
    "mcp-flux-schnell": {
      "command": "node",
      "args": ["/path/to/mcp-flux-schnell/build/index.js"],
      "env": {
        "FLUX_API_URL": "your flux api url",
        "FLUX_API_TOKEN": "your flux api token",
        "WORKING_DIR": "your working directory"
      }
    }
  }
}
```

This makes the MCP server available in all your Cursor workspaces.

TDQS

B3.1/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool 'generate_image' has a clear and distinct purpose that cannot be confused with any other tool in the set.

Naming Consistency5/5

The single tool name 'generate_image' follows a clear verb_noun pattern. With only one tool, consistency is inherently perfect as there are no other names to compare against or deviate from.

Tool Count2/5

A single tool is too few for most practical server purposes, as it severely limits functionality and flexibility. For an image generation server, typical expectations might include variations like upscaling, editing, or batch processing, making one tool feel thin and under-scoped.

Completeness2/5

The server's domain appears to be image generation, but with only a basic generation tool, there are significant gaps. Missing operations might include image editing, style variations, resolution adjustments, or batch processing, which could lead to agent failures when more complex tasks are required.

Maintenance

ActivityInactive
ResponsivenessNo issues