Skip to main content
Glama
Sign In
WujieAI MCP Server

WujieAI MCP Server

by zijin-zj
OverviewSchemaSourceRelated ServersDiscussionsAdmin
JavaScript
Hybrid

无界AI生图的MCP服务集成指南

一、服务核心功能

  1. AI图像生成：通过MCP协议，可调用无界AI数十种模型生成图像

  2. 模型信息列表：可查看无界AI数十种作画生图模型介绍

  3. 多分辨率支持：支持512~4094主流尺寸的任意宽高组合

  4. 参数自定义：可调节采样步数、采样器类型、提示词相关性等专业参数

二、快速接入流程

步骤1：获取API密钥

  1. 访问无界AI控制台

  2. 注册/登录后进入「开发者中心」

  3. 在「密钥管理」模块创建新密钥

  4. 记录生成的WUJIEAI_API_KEY

步骤2 ：环境准备

# 验证Node.js环境（要求v18.0.0或更高版本）
node -v

步骤3：Server服务配置

# 本地客户端（推荐）
{
  "mcpServers": {
    "mcp-server-wujieai": {
      "command": "npx",
      "args": ["-y", "wujieai-mcp-server"],
  	  "env": {
        "WUJIEAI_API_KEY": ${YOUR_API_KEY}
      }
    }
  }
}

# HTTP SSE长连接
{
  "mcpServers": {
    "wujie-ai-sse": {
      "url": "https://pref-gate.wujieai.com/open-platform-mcp/sse?key=${YOUR_API_KEY}"
    }
  }
}

三、开发调用示例

const result = await client.callTool({
  name: "generate_image",
  arguments: {
    prompt: "一只优雅地坐着的猫",
    model: "1013"
  }
});

四、最佳实践建议

  1. 提示词优化：

    • 使用权重标记符( )强化关键元素：(neon lights:1.3)

五、技术支持

注：具体API参数请以最新版文档为准。建议通过npm update @wujieai/wujieai-mcp-server保持SDK版本同步更新。

Available Tools

3 tools
generate_imageC

AI生成图片

Inputs: prompt (required), cfg, num, seed, +7 more.

query_generate_taskB

查询作画任务结果

Inputs: key (required).

query_model_infosB

查询作画模型信息列表

Inputs: no named parameters.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    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

    B3.3/5.0

    Scored across 3 tools

    Disambiguation5/5

    Each tool targets a distinct aspect: generating an image, querying task results, and listing model info. There is no overlap or ambiguity between them.

    Naming Consistency5/5

    All tool names follow a consistent snake_case verb_noun pattern (generate_image, query_generate_task, query_model_infos). The naming is predictable and uniform.

    Tool Count5/5

    With exactly 3 tools, the server provides a tightly scoped set that covers the essential lifecycle of image generation without unnecessary bloat. The count feels appropriate for the purpose.

    Completeness4/5

    The server covers generation, result querying, and model listing, which handles the core workflow. Missing features like task cancellation or listing all tasks are minor and not critical for basic usage.

    Maintenance

    ActivityInactive
    ResponsivenessNo recent community issues

    Resources

    Related MCP Connectors

    Related MCP Servers