Context Engineering MCP

# 传统方法 - 手动审查
context = "You are an AI assistant. You help users. You are helpful..."
# 开发者: "我觉得没问题！" 🤷

# 上下文工程方法 - AI分析
analysis = await analyze_context(context)
print(f"质量得分: {analysis.quality_score}/100")
print(f"发现的问题: {analysis.issues}")
print(f"建议: {analysis.recommendations}")

# 输出:
# 质量得分: 65/100
# 发现的问题: ['冗余表述', '指令模糊']
# 建议: ['合并角色定义', '添加具体示例']

我们的AI分析器评估以下方面：

• 语义连贯性：思想的流畅程度。
• 信息密度：令牌使用效率指标。
• 清晰度得分：可读性和可理解性。
• 相关性映射：内容与意图的匹配程度。

# 优化前
original_context = """
You are an AI assistant. You are helpful. You help users with their 
questions. When users ask questions, you provide helpful answers. 
You should be helpful and provide good answers to questions.
"""
# 令牌数: 50, 质量: 60/100

# 优化后
optimized_context = """
You are a helpful AI assistant that provides comprehensive, 
accurate answers to user questions.
"""
# 令牌数: 15 (减少70%!), 质量: 85/100

优化策略包括：

• 🎯 减少令牌：在不损失含义的前提下消除冗余。
• 💎 增强清晰度：提高指令的精确性。
• 🔗 提升相关性：优先处理重要信息。
• 📐 改进结构：优化逻辑流程。

# 创建可复用模板
template = create_template(
    name="Customer Support Agent",
    template="""
    You are a {company} support agent with {experience} of experience.
    
    Your responsibilities:
    - {primary_task}
    - {secondary_task}
    
    Communication style: {tone}
    
    Current context: {context}
    """,
    category="support",
    tags=["customer-service", "chatbot"]
)

# 在不同场景中使用
rendered = render_template(template, {
    "company": "TechCorp",
    "experience": "5 years",
    "primary_task": "Resolve technical issues",
    "secondary_task": "Ensure customer satisfaction",
    "tone": "Professional yet friendly",
    "context": "Black Friday sale period"
})

模板系统的特性包括：

• 🤖 人工智能生成模板：描述需求即可获得模板。
• 📊 使用分析：跟踪哪些模板效果最佳。
• 🔄 版本控制：可回滚到以前的版本。
• 🧪 A/B测试：比较模板性能。

处理复杂的现实场景：

# 创建多模态上下文
context = create_multimodal_context(
    text="Analyze this product image and create a description",
    images=["product_photo.jpg", "dimension_diagram.png"],
    documents=["product_specs.pdf"],
    metadata={
        "target_audience": "technical buyers",
        "tone": "professional",
        "length": "200-300 words"
    }
)

# 为每种模态自动优化
optimized = await optimize_multimodal(context)

支持的格式包括：

• 📝 文本：Markdown、纯文本、代码
• 🖼️ 图像：JPEG、PNG、WebP
• 🎵 音频：MP3、WAV（转录）
• 📹 视频：MP4（帧提取）
• 📄 文档：PDF、DOCX、XLSX

// 只需添加到你的Claude Desktop配置中：
{
  "mcpServers": {
    "context-engineering": {
      "command": "node",
      "args": ["./mcp-server/context_mcp_server.js"]
    }
  }
}

然后在Claude中使用自然语言：

• "优化我的聊天机器人上下文以提高清晰度"
• "创建一个代码审查模板"
• "分析我的AI响应速度慢的原因"
• "比较这两种提示策略"

你将拥有15个强大的工具！

# 创建专门的AI代理
agent_session = create_session("Customer Service Agent")
window = create_context_window(agent_session, max_tokens=4096)

# 添加特定角色的上下文
add_context_element(window, {
    "content": "You are Emma, a senior customer service specialist...",
    "type": "system",
    "priority": 10
})

# 添加公司知识
add_context_element(window, {
    "content": "Company policies: ...",
    "type": "system",
    "priority": 8
})

# 分析并优化
analysis = analyze_context(window)
if analysis.quality_score < 80:
    optimized = optimize_context(window, goals=["clarity", "relevance"])

结果：响应时间加快40%，客户满意度达85%。

# 优化前: 通用聊天机器人
old_prompt = "You are a chatbot. Answer questions."

# 优化后: 使用模板优化
template = generate_template(
    purpose="Technical support chatbot for SaaS platform",
    examples=["User login issues", "API integration help"],
    constraints=["Max 2 paragraphs", "Include links to docs"]
)

# 部署优化版本
optimized_bot = render_template(template, {
    "product": "CloudAPI Pro",
    "docs_url": "https://docs.cloudapi.com"
})

结果：升级率降低60%，解决问题速度提升2倍。

# 创建内容生成模板
blog_template = create_template(
    name="Technical Blog Post",
    template="""Write a {word_count}-word blog post about {topic}.
    
    Target audience: {audience}
    Tone: {tone}
    Include: {requirements}
    
    SEO keywords: {keywords}
    """,
    category="content"
)

# 生成一致的内容
for topic in topics:
    content = generate_with_template(blog_template, {
        "topic": topic,
        "word_count": 1500,
        "audience": "developers",
        "tone": "informative yet engaging",
        "requirements": ["code examples", "best practices"],
        "keywords": ["API", "integration", "tutorial"]
    })

结果：内容输出量提升5倍，质量得分始终保持在90%以上。

# 多模态研究上下文
research_context = create_multimodal_context(
    text="Analyze market trends for electric vehicles",
    documents=["market_report_2024.pdf", "competitor_analysis.xlsx"],
    images=["sales_charts.png", "technology_roadmap.jpg"],
    metadata={
        "focus_areas": ["battery technology", "charging infrastructure"],
        "output_format": "executive summary with recommendations"
    }
)

# 针对全面分析进行优化
optimized = optimize_multimodal(research_context, 
    goals=["completeness", "actionable_insights"])

结果：节省70%的时间，见解准确率达95%。

会话管理

POST   /api/sessions              # 创建新会话
GET    /api/sessions              # 列出所有会话
GET    /api/sessions/{id}         # 获取会话详情
DELETE /api/sessions/{id}         # 删除会话

上下文窗口

POST   /api/sessions/{id}/windows # 创建上下文窗口
GET    /api/contexts/{id}         # 获取上下文详情
POST   /api/contexts/{id}/elements # 添加上下文元素
DELETE /api/contexts/{id}/elements/{elem_id} # 移除元素

分析与优化

POST   /api/contexts/{id}/analyze # 分析上下文质量
POST   /api/contexts/{id}/optimize # 根据目标进行优化
POST   /api/contexts/{id}/auto-optimize # AI驱动的优化
GET    /api/optimization/{task_id} # 检查优化状态

模板管理

POST   /api/templates             # 创建模板
POST   /api/templates/generate    # AI生成模板
GET    /api/templates             # 列出模板
GET    /api/templates/{id}        # 获取模板
POST   /api/templates/{id}/render # 使用变量渲染模板
PUT    /api/templates/{id}        # 更新模板
DELETE /api/templates/{id}        # 删除模板

// 上下文工程工具
- create_context_session(name, description)
- create_context_window(session_id, max_tokens)
- add_context_element(window_id, content, type, priority)
- analyze_context(window_id)
- optimize_context(window_id, goals)
- auto_optimize_context(window_id)
- get_context_stats()

// 模板管理工具
- create_prompt_template(name, template, category)
- generate_prompt_template(purpose, examples)
- list_prompt_templates(category, tags)
- render_template(template_id, variables)

// AI指南工具 (额外功能)
- list_ai_guides()
- search_ai_guides(query)
- search_guides_with_gemini(query)
- analyze_guide(title)

AWS ECS

# 构建并推送到ECR
aws ecr get-login-password | docker login --username AWS --password-stdin $ECR_URI
docker build -t context-engineering .
docker tag context-engineering:latest $ECR_URI/context-engineering:latest
docker push $ECR_URI/context-engineering:latest

# 使用CloudFormation部署
aws cloudformation create-stack --stack-name context-engineering \
  --template-body file://aws/ecs-stack.yaml

Google Cloud Run

# 构建并部署
gcloud builds submit --tag gcr.io/$PROJECT_ID/context-engineering
gcloud run deploy context-engineering \
  --image gcr.io/$PROJECT_ID/context-engineering \
  --platform managed \
  --allow-unauthenticated

Kubernetes

# 应用清单
kubectl apply -f k8s/namespace.yaml
kubectl apply -f k8s/deployment.yaml
kubectl apply -f k8s/service.yaml
kubectl apply -f k8s/ingress.yaml