Skip to main content
Glama
enesjakozh
stefanskiasan

Together AI Image MCP Server

by stefanskiasan
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

Together AI 이미지 서버

Together AI의 이미지 생성 모델을 사용하여 이미지를 생성하는 MCP 서버입니다.

설정

  1. 종속성 설치:

지엑스피1

  1. 서버를 빌드하세요:

npm run build

Related MCP server: MCP Image Generator

구성

1. Together AI API 키

서버에는 Together AI API 키가 필요합니다. Together AI 플랫폼 에서 API 키를 받으실 수 있습니다.

2. 클라인 구성

Cline MCP 설정 파일에 서버를 추가합니다.

macOS/Linux의 경우: ~/Library/Application Support/Windsurf/User/globalStorage/saoudrizwan.claude-dev/settings/cline_mcp_settings.json

{
  "mcpServers": {
    "togetherai-image": {
      "command": "node",
      "args": ["/path/to/togetherai-image-server/build/index.js"],
      "env": {
        "TOGETHER_API_KEY": "your-api-key-here"
      },
      "disabled": false,
      "autoApprove": []
    }
  }
}

클라인에서의 사용법

서버는 다음 매개변수를 사용하여 generate_image 도구를 제공합니다.

{
  prompt: string;           // Required: Text description of the image to generate
  model?: string;          // Optional: Model to use (default: 'black-forest-labs/FLUX.1.1-pro')
  width?: number;          // Optional: Image width in pixels (default: 1024)
  height?: number;         // Optional: Image height in pixels (default: 768)
  steps?: number;         // Optional: Number of inference steps (default: 28)
  n?: number;             // Optional: Number of images to generate (default: 1)
  outputDir?: string;     // Optional: Directory where images will be saved (default: './output')
}

사용 예

Cline의 서버는 다음과 같이 사용할 수 있습니다.

Generate an image of a cat and save it to my desktop:

<use_mcp_tool>
<server_name>togeherai-image</server_name>
<tool_name>generate_image</tool_name>
<arguments>
{
  "prompt": "A cute cat sitting on a windowsill",
  "outputDir": "/Users/username/Desktop/generated-images"
}
</arguments>
</use_mcp_tool>

산출

이 도구는 다음을 포함하는 JSON 응답을 반환합니다.

  • filepath : 저장된 이미지의 전체 경로

  • filename : 저장된 이미지 파일의 이름

  • dimensions : 이미지의 원본 및 최종 치수

특징

  • Together AI의 최신 FLUX.1.1-pro 모델을 지원합니다.

  • 크기가 256픽셀 미만이면 이미지 크기를 자동으로 조정합니다.

  • 크기 조정 중에도 종횡비를 유지합니다.

  • 고품질 JPEG 출력(90% 품질)

  • 재귀적으로 출력 디렉토리를 생성합니다.

  • 이미지 크기를 포함한 자세한 메타데이터를 반환합니다.

Available Tools

1 tool
generate_imageC

Generate an image using Together AI

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYesText description of the image to generate
modelNoModel to use for generationblack-forest-labs/FLUX.1.1-pro
widthNoImage width in pixels
heightNoImage height in pixels
stepsNoNumber of inference steps
nNoNumber of images to generate
outputDirNoFull absolute path where images will be saved (e.g., /Users/username/Projects/myapp/src/assets)
formatNoOutput format for the generated imagespng

TDQS

C2.9/5.0
Behavior2/5

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

With no annotations provided, the description carries full burden for behavioral disclosure. It mentions 'Generate an image' which implies a creation/write operation, but provides no information about permissions needed, rate limits, costs, whether it's idempotent, or what happens with the generated images (e.g., are they saved locally as indicated by outputDir?). This is a significant gap for a tool with potentially complex behavior.

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

Conciseness5/5

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

The description is extremely concise - a single sentence that directly states the tool's purpose without any unnecessary words. It's perfectly front-loaded with the essential information, making it highly efficient for an agent to parse.

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?

For an image generation tool with 8 parameters and no output schema, the description is insufficient. It doesn't explain what the tool returns (e.g., file paths, success status, error handling), doesn't mention the outputDir parameter's significance for file storage, and provides no behavioral context despite the complexity implied by multiple configuration parameters. The lack of annotations exacerbates these gaps.

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?

The schema description coverage is 100%, so the schema already documents all 8 parameters thoroughly. The description adds no additional parameter information beyond what's in the schema, which is acceptable given the comprehensive schema documentation. This meets the baseline expectation when schema coverage is high.

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

Purpose4/5

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

The description clearly states the verb ('Generate') and resource ('image') with the service provider ('using Together AI'), making the purpose immediately understandable. However, with no sibling tools mentioned, it doesn't need to differentiate from alternatives, so it falls short of a perfect 5.

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?

The description provides no guidance on when to use this tool versus alternatives, prerequisites, or constraints. It simply states what the tool does without any context about appropriate use cases or limitations.

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. 1 tool updatev1.0.0
    • First observedgenerate_image
Deploy Server
One endpoint for every MCP toolRayrun runs every MCP server behind one URL and holds the credentials. Each call is decided per client, tool, and argument, then recorded.ray.runAd

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, making it impossible for an agent to misselect between non-existent alternatives.

Naming Consistency5/5

The naming pattern cannot be inconsistent with only one tool. The tool name 'generate_image' follows a verb_noun convention, which is straightforward and predictable, though there are no other tools to compare it against for consistency.

Tool Count2/5

A single tool for an image generation server feels thin and under-scoped. While it covers the core functionality, typical image generation APIs offer more operations (e.g., variations, edits, or style transfers), making this count borderline too few for the apparent domain.

Completeness2/5

The tool set is severely incomplete for an image generation domain. It only provides generation, with no obvious gaps to assess since there are no other tools, but the lack of common operations like editing, upscaling, or batch processing suggests significant coverage issues for agent workflows.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches