Image Generation MCP Server
Servidor MCP de generación de imágenes
Un servidor de Protocolo de Contexto de Modelo (MCP) que permite la generación fluida de imágenes de alta calidad utilizando el modelo Flux.1 Schnell mediante Together AI. Este servidor proporciona una interfaz estandarizada para especificar los parámetros de generación de imágenes.
Características
Generación de imágenes de alta calidad impulsada por el modelo Flux.1 Schnell
Soporte para dimensiones personalizables (ancho y alto)
Manejo claro de errores para una rápida validación y problemas de API
Fácil integración con clientes compatibles con MCP
Guardado opcional de imagen en disco en formato PNG
Related MCP server: Image Generation MCP Server
Instalación
npm install together-mcpO ejecutar directamente:
npx together-mcp@latestConfiguración
Agregue a su configuración de servidor MCP:
{
"mcpServers": {
"together-image-gen": {
"command": "npx",
"args": ["together-mcp@latest -y"],
"env": {
"TOGETHER_API_KEY": "<API KEY>"
}
}
}
}Uso
El servidor proporciona una herramienta: generate_image
Usando generate_image
Esta herramienta solo requiere un parámetro: el mensaje. Los demás parámetros son opcionales y, si no se proporcionan, se utilizan valores predeterminados razonables.
Parámetros
{
// Required
prompt: string; // Text description of the image to generate
// Optional with defaults
model?: string; // Default: "black-forest-labs/FLUX.1-schnell-Free"
width?: number; // Default: 1024 (min: 128, max: 2048)
height?: number; // Default: 768 (min: 128, max: 2048)
steps?: number; // Default: 1 (min: 1, max: 100)
n?: number; // Default: 1 (max: 4)
response_format?: string; // Default: "b64_json" (options: ["b64_json", "url"])
image_path?: string; // Optional: Path to save the generated image as PNG
}Ejemplo de solicitud mínima
Solo se requiere el mensaje:
{
"name": "generate_image",
"arguments": {
"prompt": "A serene mountain landscape at sunset"
}
}Ejemplo de solicitud completa con guardado de imagen
Anule los valores predeterminados y especifique una ruta para guardar la imagen:
{
"name": "generate_image",
"arguments": {
"prompt": "A serene mountain landscape at sunset",
"width": 1024,
"height": 768,
"steps": 20,
"n": 1,
"response_format": "b64_json",
"model": "black-forest-labs/FLUX.1-schnell-Free",
"image_path": "/path/to/save/image.png"
}
}Formato de respuesta
La respuesta será un objeto JSON que contendrá:
{
"id": string, // Generation ID
"model": string, // Model used
"object": "list",
"data": [
{
"timings": {
"inference": number // Time taken for inference
},
"index": number, // Image index
"b64_json": string // Base64 encoded image data (if response_format is "b64_json")
// OR
"url": string // URL to generated image (if response_format is "url")
}
]
}Si se proporcionó image_path y el guardado se realizó correctamente, la respuesta incluirá la confirmación de la ubicación de guardado.
Valores predeterminados
Si no se especifica en la solicitud, se utilizan estos valores predeterminados:
Modelo: "black-forest-labs/FLUX.1-schnell-Free"
ancho: 1024
altura: 768
pasos: 1
n: 1
formato_de_respuesta: "b64_json"
Notas importantes
Solo se requiere el parámetro
promptTodos los parámetros opcionales utilizan valores predeterminados si no se proporcionan
Cuando se proporcionan, los parámetros deben cumplir con sus restricciones (por ejemplo, rangos de ancho/alto)
Las respuestas Base64 pueden ser grandes: use el formato URL para imágenes más grandes
Al guardar imágenes, asegúrese de que el directorio especificado exista y se pueda escribir en él.
Prerrequisitos
Node.js >= 16
Clave API de Together AI
Inicie sesión en api.together.xyz
Haga clic en "Crear" para generar una nueva clave API
Copie la clave generada para usarla en su configuración de MCP
Dependencias
{
"@modelcontextprotocol/sdk": "0.6.0",
"axios": "^1.6.7"
}Desarrollo
Clonar y construir el proyecto:
git clone https://github.com/manascb1344/together-mcp-server
cd together-mcp-server
npm install
npm run buildScripts disponibles
npm run build- Construye el proyecto TypeScriptnpm run watch: vigila los cambios y reconstruyenpm run inspector- Ejecutar el inspector MCP
Contribuyendo
¡Agradecemos sus contribuciones! Siga estos pasos:
Bifurcar el repositorio
Crear una nueva rama (
feature/my-new-feature)Confirme sus cambios
Empuja la rama hacia tu tenedor
Abrir una solicitud de extracción
Las solicitudes de funciones y los informes de errores se pueden enviar a través de GitHub Issues. Por favor, revise los problemas existentes antes de crear uno nuevo.
Para cambios significativos, primero abra un problema para discutir los cambios propuestos.
Licencia
Este proyecto está licenciado bajo la Licencia MIT. Consulte el archivo de LICENCIA para más detalles.
Available Tools
1 toolgenerate_imageC
Generate an image using Together AI API
| Name | Required | Description | Default |
|---|---|---|---|
| prompt | Yes | Text prompt for image generation | |
| model | No | Model to use for generation (default: black-forest-labs/FLUX.1-schnell-Free) | |
| width | No | Image width (default: 1024) | |
| height | No | Image height (default: 768) | |
| steps | No | Number of inference steps (default: 1) | |
| n | No | Number of images to generate (default: 1) | |
| response_format | No | Response format (default: b64_json) | |
| image_path | No | Optional path to save the generated image as PNG |
TDQS
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
With no annotations provided, the description carries the full burden of behavioral disclosure. It mentions the API provider but fails to describe critical behaviors like rate limits, authentication requirements, cost implications, error handling, or what happens when saving to 'image_path'. This leaves significant gaps for a tool with 8 parameters and no output schema.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
The description is extremely concise with a single sentence that directly states the tool's purpose. There is zero wasted language, and it's front-loaded with the core functionality, making it highly efficient.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Given the complexity (8 parameters, no output schema, no annotations), the description is insufficient. It doesn't explain return values, error cases, or behavioral nuances, leaving the agent with incomplete information for proper tool invocation in a real-world context.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Schema description coverage is 100%, so the schema fully documents all 8 parameters. The description adds no additional parameter semantics beyond what's already in the schema, meeting the baseline score of 3 for high schema coverage without extra value.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
The description clearly states the action ('Generate an image') and the target resource ('using Together AI API'), providing a specific verb+resource combination. However, with no sibling tools mentioned, there's no explicit differentiation from alternatives, preventing a perfect score.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
The description provides no guidance on when to use this tool versus alternatives, prerequisites, or context for invocation. It simply states what the tool does without any usage instructions or exclusions.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
1 tool update
v0.1.7- First observed
generate_image
TDQS
Scored across 1 tool
With only one tool, there is no possibility of ambiguity or overlap between tools. The single tool has a clear and distinct purpose, making it impossible for an agent to misselect between multiple options.
Since there is only one tool, naming consistency is inherently perfect. The tool name 'generate_image' follows a clear verb_noun pattern, and there are no other tools to compare it against for inconsistency.
A single tool is too few for a server named 'Image Generation MCP Server', which suggests a broader scope. While the tool covers basic generation, the lack of additional tools (e.g., for editing, listing, or managing images) makes the surface feel thin and incomplete for the implied domain.
The server is severely incomplete for an image generation domain. It only provides a generate_image tool, with no coverage for related operations like listing generated images, editing parameters, deleting images, or handling variations. This creates significant gaps that will likely cause agent failures in broader workflows.
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 Connectors
MCP server for Flux AI image generation
Official FLUX MCP server. Generate, edit, vary, and browse images from Black Forest Labs.
A Model Context Protocol server for Wix AI tools
A comprehensive Model Context Protocol (MCP) server that enables AI assistants to interact with yo…
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceImplements a Model Context Protocol (MCP) server powered by Flux API from Cephalon Cloud, enabling users to utilize advanced AI capabilities through standardized communication.31MIT
- AlicenseBqualityDmaintenanceA Model Context Protocol server that enables generation of high-quality images using the Flux.1 Schnell model via Together AI, allowing users to create images from text prompts with customizable dimensions.118MIT
- FlicenseDqualityDmaintenanceA Model Context Protocol server that generates images using Replicate's FLUX model and stores them in Cloudflare R2, allowing users to create images through simple prompts and retrieve accessible URLs.111-
- AlicenseNot gradedqualityDmaintenanceA server that enables generating images through the Replicate API by calling the Flux Schnell model via the Model Context Protocol (MCP).3MIT