Generate images using Baidu's iRAG API through a standardized MCP interface.
一个基于百度iRAG图片生成API的MCP(Model Context Protocol)服务器,允许MCP客户端(如Claude Desktop)通过标准化接口调用百度的图片生成服务。
在使用前,请务必进行真实API测试!
基础测试只验证服务器启动,要确保完全可用,需要:
npm run test:api
进行真实API测试详细设置指南请查看:FINAL_SETUP.md
git clone <repository-url>
cd irag-mcp-server
npm install
npm run build
bce-v3/ALTAK-****/****
)复制环境变量模板:
cp .env.example .env
编辑 .env
文件:
# 必需配置
BAIDU_API_KEY=bce-v3/ALTAK-your-access-key/your-secret-key
# 图片资源配置
RESOURCE_MODE=local # local: 保存到本地文件 | url: 仅返回URL和base64
BASE_PATH= # 自定义保存路径(可选,默认为桌面/irag-images)
MODEL=irag-1.0 # 默认模型: irag-1.0 | flux.1-schnell
# 可选配置
SERVER_NAME=irag-mcp-server
SERVER_VERSION=1.0.0
LOG_LEVEL=info
LOG_FILE=logs/server.log
API_TIMEOUT=30000
MAX_RETRIES=3
irag-1.0
: 百度自研模型,通用性好,速度快flux.1-schnell
: 支持更多高级参数,质量更高# 开发模式
npm run dev
# 生产模式
npm start
在Claude Desktop的配置文件中添加:
Windows: %APPDATA%\Claude\claude_desktop_config.json
macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"irag-image-generator": {
"command": "node",
"args": ["/path/to/irag-mcp-server/dist/index.js"],
"env": {
"BAIDU_API_KEY": "bce-v3/ALTAK-your-access-key/your-secret-key"
}
}
}
}
生成图片的MCP工具。
参数名 | 类型 | 必需 | 默认值 | 描述 |
---|---|---|---|---|
prompt | string | ✅ | - | 图片生成提示词 |
refer_image | string | ❌ | - | 参考图片URL |
n | integer | ❌ | 1 | 生成图片数量(1-4) |
size | string | ❌ | 1024x1024 | 图片尺寸 |
steps | integer | ❌ | - | 采样步数(1-50,仅flux.1-schnell) |
seed | integer | ❌ | - | 随机种子(仅flux.1-schnell) |
guidance | number | ❌ | 3.5 | 指导密度值(0-30,仅flux.1-schnell) |
注意: 模型通过配置文件的MODEL
参数设置,不在请求中指定。
512x512
, 768x768
, 1024x768
, 1024x1024
{
"name": "generate_image",
"arguments": {
"prompt": "一只可爱的橘猫坐在窗台上,阳光透过窗户洒在它身上",
"size": "1024x1024",
"n": 2
}
}
src/
├── client/ # API客户端
├── config/ # 配置管理
├── server/ # MCP服务器
├── types/ # 类型定义
├── utils/ # 工具函数
├── __tests__/ # 测试文件
└── index.ts # 主入口
# 开发模式运行
npm run dev
# 构建项目
npm run build
# 运行测试
npm test
# 监听测试
npm run test:watch
# 代码检查
npm run lint
# 修复代码风格
npm run lint:fix
# 清理构建文件
npm run clean
运行所有测试:
npm test
查看测试覆盖率:
npm test -- --coverage
API Key无效
bce-v3/ALTAK-****/****
连接超时
API_TIMEOUT
配置值图片生成失败
Base64验证错误
MCP客户端连接问题
npm run build
)设置日志级别为debug:
LOG_LEVEL=debug
查看详细的API调用日志和图片下载过程。
MIT License
欢迎提交Issue和Pull Request!
Up-to-date documentation for your coding agent. Covers 1000s of public repos and sites. Built by ref.tools
MCP Language Server gives MCP enabled clients access to semantic tools like get definition, references, rename, and diagnostics.
A server for CodeFuse-CGM, a graph-integrated large language model designed for repository-level software engineering tasks.
Make your AI agent speak every language on the planet, using Lingo.dev Localization Engine.
Manipulate Adventure Game Studio (AGS) compiled room (.crm) files to enable AI-powered game development.
MCP Server to control and interact with Unity3d Game Engine for game development
A server for Zep, a long-term memory store for AI applications, requiring a ZEP_API_KEY for access.
Provides seamless integration with SonarQube Server or Cloud, and enables analysis of code snippets directly within the agent context
Turns any Swagger/OpenAPI REST endpoint with a yaml/json definition into an MCP Server with Langchain/Langflow integration automatically.
A secure command-line interface server for the Model Context Protocol (MCP) that allows AI models to interact with a user's terminal.