Skip to main content
Glama
enesjakozh
zym9863

Together AI Image Server

by zym9863
OverviewSchemaRelated ServersScoreDiscussions
TypeScript
Remote

Together AI 图像服务器

English |简体中文

基于 TypeScript 的 MCP（模型上下文协议）服务器，用于使用 Together AI API 生成图像。

概述

该服务器提供了一个简单的接口，可以通过 MCP 协议使用 Together AI 的图像生成模型生成图像。它允许 Claude 和其他兼容 MCP 的助手根据文本提示生成图像。

Related MCP server: gemini-nano-banana-mcp

特征

工具

  • generate_image - 根据文本提示生成图像

    • 将文本提示作为必需参数

    • 用于控制生成步骤和图像数量的可选参数

    • 返回生成图像的 URL 和本地路径

先决条件

  • Node.js（建议使用 v14 或更高版本）

  • Together AI API 密钥

安装

# Clone the repository
git clone https://github.com/zym9863/together-ai-image-server.git
cd together-ai-image-server

# Install dependencies
npm install

配置

将您的 Together AI API 密钥设置为环境变量：

# On Linux/macOS
export TOGETHER_API_KEY="your-api-key-here"

# On Windows (Command Prompt)
set TOGETHER_API_KEY=your-api-key-here

# On Windows (PowerShell)
$env:TOGETHER_API_KEY="your-api-key-here"

或者，您可以在项目根目录中创建一个.env文件：

TOGETHER_API_KEY=your-api-key-here

发展

构建服务器：

npm run build

对于使用自动重建的开发：

npm run watch

与 Claude Desktop 一起使用

要与 Claude Desktop 一起使用，请添加服务器配置：

在 macOS 上： ~/Library/Application Support/Claude/claude_desktop_config.json
在 Windows 上： %APPDATA%/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "Together AI Image Server": {
      "command": "/path/to/together-ai-image-server/build/index.js"
    }
  }
}

将/path/to/together-ai-image-server替换为安装的实际路径。

调试

由于 MCP 服务器通过 stdio 进行通信，调试起来可能比较困难。我们推荐使用MCP Inspector ，它以包脚本的形式提供：

npm run inspector

检查器将提供一个 URL 来访问浏览器中的调试工具。

API 参考

生成图像

使用 Together AI 的图像生成 API 根据文本提示生成图像。

参数：

  • prompt （字符串，必需）：图像生成的文本提示

  • steps （数字，可选，默认值：4）：扩散步骤数（1-4）

  • n （数字，可选，默认值：1）：要生成的图像数量（1-4）

返回：

JSON 对象包含：

  • image_urls ：生成的图像的 URL 数组

  • local_paths ：本地缓存图像的路径数组

执照

麻省理工学院

贡献

欢迎贡献代码！欢迎提交 Pull 请求。

Available Tools

1 tool
generate_imageC

Generate image from text prompt using Together AI API

ParametersJSON Schema
NameRequiredDescriptionDefault
nNoNumber of images to generate (default: 1, max: 4)
stepsNoNumber of diffusion steps (default: 4)
promptYesText prompt for image generation

TDQS

C2.9/5.0
Behavior1/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations are provided, so the description carries full burden. It only mentions the external API but does not disclose any behavioral traits such as rate limits, authentication needs, what happens under the hood, or potential side effects like image generation limits or API costs.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

The description is a single sentence that is concise and front-loaded with the core action. However, it is too short to cover necessary details, but for what it states, it is efficient.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness2/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Given the absence of an output schema and annotations, the description is incomplete. It provides no information about what the tool returns (e.g., image URLs or base64), any limitations, or error conditions. The user would need to guess or rely on external knowledge.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters3/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

All three parameters have descriptions in the input schema (100% coverage). The description adds no extra meaning beyond the schema, which already explains 'prompt', 'n', and 'steps'. Baseline 3 is appropriate.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

The description clearly states the tool's purpose: generating an image from a text prompt using the Together AI API. The verb 'generate' and resource 'image' are specific, and mentioning the API adds context. No siblings exist, so differentiation is not needed.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines2/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

No guidance is provided on when to use or avoid this tool. There is no mention of prerequisites, alternatives, or when not to use it. The description simply states what it does without contextual usage advice.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server
RayrunBuild, deploy, and operate MCP servers without becoming an infrastructure team.ray.runAd

TDQS

B3.1/5.0
Disambiguation5/5

With only one tool, there is no possibility of confusion between tools. The tool's purpose is clearly defined.

Naming Consistency5/5

The single tool 'generate_image' follows a clear verb_noun pattern, which is consistent by default.

Tool Count2/5

The server has only one tool, which is too few for a typical image generation service. Users would likely expect additional tools for model selection, image variants, or status retrieval.

Completeness2/5

The tool surface is severely incomplete; a comprehensive image generation server would typically include tools for listing models, configuring generation parameters, and possibly managing generated images.

Maintenance

ActivityInactive
ResponsivenessNo issues

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

Related MCP Servers

Appeared in Searches

Latest Blog Posts

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/zym9863/together-ai-image-server'

If you have feedback or need assistance with the MCP directory API, please join our Discord server