Skip to main content
Glama
enesjakozh
mikeyny

Image Generation MCP Server

by mikeyny
OverviewSchemaSourceRelated ServersDiscussionsAdmin
TypeScript
Hybrid

이미지 생성 MCP 서버

Replicate의 black-forest-labs/flux-schnell 모델을 사용하여 이미지를 생성하기 위한 MCP(Model Context Protocol) 서버 구현입니다.

이상적으로는 Cursor의 MCP 기능과 함께 사용하는 것이 좋지만, 모든 MCP 클라이언트와 함께 사용할 수 있습니다.

특징

  • 텍스트 프롬프트에서 이미지 생성

  • 구성 가능한 이미지 매개변수(해상도, 종횡비, 품질)

  • 생성된 이미지를 지정된 디렉토리에 저장합니다.

  • 전체 MCP 프로토콜 준수

  • 오류 처리 및 검증

Related MCP server: replicate-flux-mcp

필수 조건

  • 노드.js 16+

  • API 토큰 복제

  • MCP용 TypeScript SDK

설정

  1. 저장소를 복제합니다

  2. 종속성 설치:

    지엑스피1

  3. apiToken 상수를 업데이트하여 src/imageService.ts 의 코드에 Replicate API 토큰을 직접 추가합니다.

    // No environment variables are used since they can't be easily set in cursor
const apiToken = "your-replicate-api-token-here";

    참고: Claude와 함께 사용하는 경우 루트 디렉토리에 .env 파일을 만들고 거기에 API 토큰을 설정할 수 있습니다.

    REPLICATE_API_TOKEN=your-replicate-api-token-here

    그런 다음 프로젝트를 빌드합니다.

    npm run build

용법

커서와 함께 사용하려면:

  1. 설정으로 이동

  2. 기능 선택

  3. "MCP 서버"까지 아래로 스크롤하세요.

  4. "새 MCP 서버 추가"를 클릭하세요.

  5. 유형을 "명령"으로 설정하세요

  6. 명령을 다음으로 설정하세요: node ./path/to/dist/server.js

API 매개변수

매개변수

유형

필수의

기본

설명

prompt

끈

예

-

이미지 생성을 위한 텍스트 프롬프트

output_dir

끈

예

-

생성된 이미지를 저장할 서버 디렉토리 경로

go_fast

부울

아니요

거짓

더 빠른 생성 모드 활성화

megapixels

끈

아니요

"1"

해상도 품질("1", "2", "4")

num_outputs

숫자

아니요

1

생성할 이미지 수(1-4)

aspect_ratio

끈

아니요

"1:1"

종횡비("1:1", "4:3", "16:9")

output_format

끈

아니요

"웹피"

이미지 형식("webp", "png", "jpeg")

output_quality

숫자

아니요

80

압축 품질(1-100)

num_inference_steps

숫자

아니요

4

노이즈 제거 단계 수(4-20)

예제 요청

{
  "prompt": "black forest gateau cake spelling out 'FLUX SCHNELL'",
  "output_dir": "/var/output/images",
  "filename": "black_forest_cake",
  "output_format": "webp"
  "go_fast": true,
  "megapixels": "1",
  "num_outputs": 2,
  "aspect_ratio": "1:1"
}

예시 응답

{
  "image_paths": [
    "/var/output/images/output_0.webp",
    "/var/output/images/output_1.webp"
  ],
  "metadata": {
    "model": "black-forest-labs/flux-schnell",
    "inference_time_ms": 2847
  }
}

오류 처리

서버는 다음과 같은 오류 유형을 처리합니다.

  • 검증 오류(잘못된 매개변수)

  • API 오류(API 문제 복제)

  • 서버 오류(파일 시스템, 권한)

  • 알 수 없는 오류(예상치 못한 문제)

각 오류 응답에는 다음이 포함됩니다.

  • 오류 코드

  • 사람이 읽을 수 있는 메시지

  • 자세한 오류 정보

특허

아이에스씨

Available Tools

1 tool
generate-imageC

Generate an image based on a prompt

ParametersJSON Schema
NameRequiredDescriptionDefault
promptYes
output_dirYesFull absolute path to output directory. For Windows, use double backslashes like 'C:\\Users\\name\\path'. For Unix/Mac use '/path/to/dir'. Always use the proper path otherwise you will get an error.
filenameNoBase filename to save the image(s) with
go_fastNo
megapixelsNo
num_outputsNo
aspect_ratioNo
output_formatNo
output_qualityNo
num_inference_stepsNo

TDQS

C2.8/5.0
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 the core action (generating images from prompts) but lacks critical behavioral details like whether this is a local or cloud operation, rate limits, authentication requirements, error handling, or what happens when files are saved. The description doesn't contradict annotations since none exist.

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 at just 5 words, front-loaded with the core functionality. Every word earns its place, and there's no wasted text or redundancy.

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 a complex tool with 10 parameters, no annotations, no output schema, and low schema description coverage, the description is severely inadequate. It doesn't explain what the tool returns, how outputs are structured, error conditions, or provide enough context for an agent to use it effectively beyond the most basic invocation.

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

Parameters2/5

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

With only 20% schema description coverage, the description must compensate but fails to do so. It mentions 'based on a prompt' which hints at one parameter but doesn't explain the other 9 parameters or their relationships. The description adds minimal value beyond what's already in the schema.

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 tool's purpose with a specific verb ('generate') and resource ('image'), and specifies it's based on a prompt. It's unambiguous about what the tool does, though it doesn't distinguish from siblings since there are none.

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, nor any context about prerequisites or limitations. It simply states what the tool does without indicating appropriate use cases.

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 update
    • 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

B3/5.0

Scored across 1 tool

Disambiguation5/5

With only one tool, there is no possibility of confusion or overlap between tools. The single tool 'generate-image' has a clear and distinct purpose for image generation based on prompts.

Naming Consistency5/5

The single tool name 'generate-image' follows a clear verb_noun pattern. Since there is only one tool, consistency is inherently perfect with no deviations or mixed conventions to evaluate.

Tool Count2/5

A single tool is too few for a server named 'Image Generation MCP Server', which suggests a broader scope. While it covers basic generation, typical image generation domains might include variations, edits, or management tools, making this feel thin and incomplete.

Completeness2/5

The tool surface is severely incomplete for image generation. It only provides generation, with no tools for editing, resizing, filtering, or managing images, leaving obvious gaps that will limit agent capabilities in this domain.

Maintenance

ActivityInactive
ResponsivenessNo issues

Resources

Related MCP Connectors

Related MCP Servers

Appeared in Searches