feat: Add automatic developer-focused system prompt

When using the Gemini MCP server from Claude Code, it now automatically
injects a developer-focused system prompt similar to Claude Code's own
behavior. This ensures Gemini responds with the same developer mindset:

- Expert software development knowledge
- Clean code practices
- Debugging and problem-solving focus
- Clear technical explanations
- Architecture and design understanding
- Performance optimization expertise

The system prompt is automatically applied when no custom system prompt
is provided, making the integration seamless for Claude Code users.

🤖 Generated with [Claude Code](https://claude.ai/code)

Co-Authored-By: Claude <noreply@anthropic.com>

README.md

@@ -19,6 +19,7 @@ See [MCP_DISCOVERY.md](MCP_DISCOVERY.md) for detailed information about how Clau
 - **List Models**: View all available Gemini models
 - **Configurable Parameters**: Adjust temperature, max tokens, and model selection
 - **System Prompts**: Support for system prompts to set context
+- **Developer Context**: Automatically uses developer-focused system prompt for Claude Code integration
 
 ## Installation
 
@@ -146,6 +147,7 @@ Other available models:
 - If a model returns a blocked response, the server will indicate the finish reason
 - The server estimates tokens as ~4 characters per token
 - Maximum context window is 1 million tokens (~4 million characters)
+- When no system prompt is provided, the server automatically uses a developer-focused prompt similar to Claude Code
 
 ## Tips for Claude Code Users
 

gemini_server.py

@@ -21,6 +21,20 @@ import google.generativeai as genai
 DEFAULT_MODEL = "gemini-2.5-pro-preview-06-05"
 MAX_CONTEXT_TOKENS = 1000000  # 1M tokens
 
+# Developer-focused system prompt for Claude Code usage
+DEVELOPER_SYSTEM_PROMPT = """You are an expert software developer and code analyst, similar to Claude Code. 
+You excel at:
+- Writing clean, efficient, and well-documented code
+- Debugging and solving complex programming problems
+- Explaining technical concepts clearly
+- Following best practices and design patterns
+- Providing thoughtful code reviews and suggestions
+- Understanding system architecture and design
+- Helping with testing strategies and implementation
+- Optimizing performance and identifying bottlenecks
+
+You should be direct, helpful, and focused on practical solutions. When analyzing code, provide actionable insights and concrete improvements. Always consider the broader context and long-term maintainability."""
+
 
 class GeminiChatRequest(BaseModel):
     """Request model for Gemini chat"""
@@ -202,10 +216,12 @@ async def handle_call_tool(name: str, arguments: Dict[str, Any]) -> List[TextCon
                 }
             )
             
-            # Prepare the prompt
-            full_prompt = request.prompt
+            # Prepare the prompt with automatic developer context if no system prompt provided
             if request.system_prompt:
                 full_prompt = f"{request.system_prompt}\n\n{request.prompt}"
+            else:
+                # Auto-inject developer system prompt for better Claude Code integration
+                full_prompt = f"{DEVELOPER_SYSTEM_PROMPT}\n\n{request.prompt}"
             
             # Generate response
             response = model.generate_content(full_prompt)
@@ -262,8 +278,8 @@ async def handle_call_tool(name: str, arguments: Dict[str, Any]) -> List[TextCon
                 }
             )
             
-            # Prepare the full prompt
-            system_prompt = request.system_prompt or "You are an expert code analyst. Provide detailed, accurate analysis of the provided code."
+            # Prepare the full prompt with enhanced developer context
+            system_prompt = request.system_prompt or DEVELOPER_SYSTEM_PROMPT
             full_prompt = f"{system_prompt}\n\nCode to analyze:\n\n{code_context}\n\nQuestion/Request: {request.question}"
             
             # Generate response

test_developer_context.py

@@ -0,0 +1,87 @@
+#!/usr/bin/env python3
+"""
+Test script to verify developer context is properly injected
+"""
+
+import os
+import asyncio
+from gemini_server import configure_gemini, handle_call_tool
+
+
+async def test_developer_context():
+    """Test the developer context system prompt"""
+    print("Testing Developer Context in Gemini MCP Server...")
+    print("-" * 50)
+    
+    # Test configuration
+    try:
+        configure_gemini()
+        print("✓ Gemini API configured successfully")
+    except Exception as e:
+        print(f"✗ Failed to configure Gemini API: {e}")
+        return
+    
+    # Test 1: Chat without explicit system prompt (should use developer prompt)
+    print("\n1. Testing chat WITHOUT system prompt (should auto-inject developer context)...")
+    result = await handle_call_tool("chat", {
+        "prompt": "Write a Python function to reverse a linked list. Include comments.",
+        "temperature": 0.3,
+        "max_tokens": 500
+    })
+    print("Response preview:")
+    print(result[0].text[:400] + "..." if len(result[0].text) > 400 else result[0].text)
+    
+    # Test 2: Chat WITH explicit system prompt (should use provided prompt)
+    print("\n2. Testing chat WITH custom system prompt...")
+    result = await handle_call_tool("chat", {
+        "prompt": "Write a haiku about coding",
+        "system_prompt": "You are a creative poet who writes about technology.",
+        "temperature": 0.9,
+        "max_tokens": 100
+    })
+    print("Response:")
+    print(result[0].text)
+    
+    # Test 3: Code analysis without system prompt (should use developer prompt)
+    print("\n3. Testing analyze_code WITHOUT system prompt...")
+    test_code = '''
+def bubble_sort(arr):
+    n = len(arr)
+    for i in range(n):
+        for j in range(0, n-i-1):
+            if arr[j] > arr[j+1]:
+                arr[j], arr[j+1] = arr[j+1], arr[j]
+    return arr
+'''
+    
+    result = await handle_call_tool("analyze_code", {
+        "code": test_code,
+        "question": "Review this code and suggest improvements",
+        "temperature": 0.3
+    })
+    print("Response preview:")
+    print(result[0].text[:500] + "..." if len(result[0].text) > 500 else result[0].text)
+    
+    # Test 4: Code analysis WITH custom system prompt
+    print("\n4. Testing analyze_code WITH custom system prompt...")
+    result = await handle_call_tool("analyze_code", {
+        "code": test_code,
+        "question": "Is this code correct?",
+        "system_prompt": "You are a beginner-friendly tutor. Explain things simply.",
+        "temperature": 0.5
+    })
+    print("Response preview:")
+    print(result[0].text[:400] + "..." if len(result[0].text) > 400 else result[0].text)
+    
+    print("\n" + "-" * 50)
+    print("Developer context tests completed!")
+
+
+if __name__ == "__main__":
+    # Check for API key
+    if not os.getenv("GEMINI_API_KEY"):
+        print("Error: GEMINI_API_KEY environment variable is not set")
+        print("Please set it with: export GEMINI_API_KEY='your-api-key'")
+        exit(1)
+    
+    asyncio.run(test_developer_context())