docs: Improve Quick Start instructions for better clarity

- Add explicit step to clone the repository first
- Include instructions for accessing config via Claude Desktop UI
- Clarify that users must replace placeholder paths with actual paths
- Add note to remember the cloned directory path

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

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

README.md

@@ -13,11 +13,27 @@ This server acts as a developer assistant that augments Claude Code when you nee
 
 ## 🚀 Quick Start for Claude Code
 
-### 1. Configure in Claude Desktop
+### 1. Clone the Repository
 
-Add to your Claude Desktop configuration file:
+First, clone this repository to your local machine:
+```bash
+git clone https://github.com/BeehiveInnovations/gemini-mcp-server.git
+cd gemini-mcp-server
+```
 
-**macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
+Note the full path to this directory - you'll need it for the configuration.
+
+### 2. Configure in Claude Desktop
+
+You can access the configuration file in two ways:
+- **Through Claude Desktop**: Open Claude Desktop → Settings → Developer → Edit Config
+- **Direct file access**: 
+  - **macOS**: `~/Library/Application Support/Claude/claude_desktop_config.json`
+  - **Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
+
+Add the following configuration, replacing the path with your actual directory path:
+
+**macOS**:
 ```json
 {
   "mcpServers": {
@@ -31,7 +47,7 @@ Add to your Claude Desktop configuration file:
 }
 ```
 
-**Windows**: `%APPDATA%\Claude\claude_desktop_config.json`
+**Windows**:
 ```json
 {
   "mcpServers": {
@@ -45,18 +61,20 @@ Add to your Claude Desktop configuration file:
 }
 ```
 
-### 2. Restart Claude Desktop
+**Important**: Replace `/path/to/gemini-mcp-server` with the actual path where you cloned the repository.
+
+### 3. Restart Claude Desktop
 
 After adding the configuration, restart Claude Desktop. You'll see "gemini" in the MCP servers list.
 
-### 3. Add to Claude Code
+### 4. Add to Claude Code
 
 To make the server available in Claude Code, run:
 ```bash
 claude mcp add-from-claude-desktop -s user
 ```
 
-### 4. Start Using Natural Language
+### 5. Start Using Natural Language
 
 Just talk to Claude naturally:
 - "Use Gemini to analyze this large file..."

tests/conftest.py

@@ -0,0 +1,28 @@
+"""
+Pytest configuration for Gemini MCP Server tests
+"""
+
+import sys
+import os
+from pathlib import Path
+
+# Ensure the parent directory is in the Python path for imports
+parent_dir = Path(__file__).resolve().parent.parent
+if str(parent_dir) not in sys.path:
+    sys.path.insert(0, str(parent_dir))
+
+# Set dummy API key for tests if not already set
+if "GEMINI_API_KEY" not in os.environ:
+    os.environ["GEMINI_API_KEY"] = "dummy-key-for-tests"
+
+# Configure asyncio for Windows compatibility
+if sys.platform == "win32":
+    import asyncio
+    asyncio.set_event_loop_policy(asyncio.WindowsSelectorEventLoopPolicy())
+
+# Pytest configuration
+def pytest_configure(config):
+    """Configure pytest with custom markers"""
+    config.addinivalue_line(
+        "markers", "asyncio: mark test as async"
+    )

tests/test_gemini_server.py

@@ -7,11 +7,15 @@ import json
 from unittest.mock import Mock, patch, AsyncMock
 from pathlib import Path
 import sys
+import os
 
-# Add parent directory to path for imports
-sys.path.append(str(Path(__file__).parent.parent))
+# Add parent directory to path for imports in a cross-platform way
+parent_dir = Path(__file__).resolve().parent.parent
+if str(parent_dir) not in sys.path:
+    sys.path.insert(0, str(parent_dir))
 
-from gemini_server import (
+try:
+    from gemini_server import (
     GeminiChatRequest,
     CodeAnalysisRequest,
     read_file_content,
@@ -21,6 +25,27 @@ from gemini_server import (
     DEVELOPER_SYSTEM_PROMPT,
     DEFAULT_MODEL
 )
+except ImportError as e:
+    # If import fails, try alternative import method
+    import importlib.util
+    spec = importlib.util.spec_from_file_location(
+        "gemini_server", 
+        parent_dir / "gemini_server.py"
+    )
+    gemini_server = importlib.util.module_from_spec(spec)
+    sys.modules["gemini_server"] = gemini_server
+    spec.loader.exec_module(gemini_server)
+    
+    from gemini_server import (
+        GeminiChatRequest,
+        CodeAnalysisRequest,
+        read_file_content,
+        prepare_code_context,
+        handle_list_tools,
+        handle_call_tool,
+        DEVELOPER_SYSTEM_PROMPT,
+        DEFAULT_MODEL
+    )
 
 
 class TestModels:
@@ -66,7 +91,7 @@ class TestFileOperations:
     def test_read_file_content_success(self, tmp_path):
         """Test successful file reading"""
         test_file = tmp_path / "test.py"
-        test_file.write_text("def hello():\n    return 'world'")
+        test_file.write_text("def hello():\n    return 'world'", encoding='utf-8')
         
         content = read_file_content(str(test_file))
         assert "=== File:" in content
@@ -75,7 +100,11 @@ class TestFileOperations:
     
     def test_read_file_content_not_found(self):
         """Test reading non-existent file"""
-        content = read_file_content("/nonexistent/file.py")
+        # Use a path that's guaranteed not to exist on any platform
+        nonexistent_path = os.path.join(
+            os.path.sep, "nonexistent_dir_12345", "nonexistent_file.py"
+        )
+        content = read_file_content(nonexistent_path)
         assert "Error: File not found" in content
     
     def test_read_file_content_directory(self, tmp_path):
@@ -86,9 +115,9 @@ class TestFileOperations:
     def test_prepare_code_context_with_files(self, tmp_path):
         """Test preparing context from files"""
         file1 = tmp_path / "file1.py"
-        file1.write_text("print('file1')")
+        file1.write_text("print('file1')", encoding='utf-8')
         file2 = tmp_path / "file2.py"
-        file2.write_text("print('file2')")
+        file2.write_text("print('file2')", encoding='utf-8')
         
         context = prepare_code_context([str(file1), str(file2)], None)
         assert "file1.py" in context
@@ -106,7 +135,7 @@ class TestFileOperations:
     def test_prepare_code_context_mixed(self, tmp_path):
         """Test preparing context from both files and code"""
         test_file = tmp_path / "test.py"
-        test_file.write_text("# From file")
+        test_file.write_text("# From file", encoding='utf-8')
         code = "# Direct code"
         
         context = prepare_code_context([str(test_file)], code)
@@ -136,7 +165,7 @@ class TestToolHandlers:
         assert "Unknown tool" in result[0].text
     
     @pytest.mark.asyncio
-    @patch('gemini_server.genai.GenerativeModel')
+    @patch('google.generativeai.GenerativeModel')
     async def test_handle_call_tool_chat_success(self, mock_model):
         """Test successful chat tool call"""
         # Mock the response
@@ -163,7 +192,7 @@ class TestToolHandlers:
         assert call_args['generation_config']['temperature'] == 0.5
     
     @pytest.mark.asyncio
-    @patch('gemini_server.genai.GenerativeModel')
+    @patch('google.generativeai.GenerativeModel')
     async def test_handle_call_tool_chat_with_developer_prompt(self, mock_model):
         """Test chat tool uses developer prompt when no system prompt provided"""
         mock_response = Mock()
@@ -190,12 +219,12 @@ class TestToolHandlers:
         assert "Must provide either 'files' or 'code'" in result[0].text
     
     @pytest.mark.asyncio
-    @patch('gemini_server.genai.GenerativeModel')
+    @patch('google.generativeai.GenerativeModel')
     async def test_handle_call_tool_analyze_code_success(self, mock_model, tmp_path):
         """Test successful code analysis"""
         # Create test file
         test_file = tmp_path / "test.py"
-        test_file.write_text("def hello(): pass")
+        test_file.write_text("def hello(): pass", encoding='utf-8')
         
         # Mock response
         mock_response = Mock()
@@ -215,7 +244,7 @@ class TestToolHandlers:
         assert result[0].text == "Analysis result"
     
     @pytest.mark.asyncio
-    @patch('gemini_server.genai.list_models')
+    @patch('google.generativeai.list_models')
     async def test_handle_call_tool_list_models(self, mock_list_models):
         """Test listing models"""
         # Mock model data
@@ -240,7 +269,7 @@ class TestErrorHandling:
     """Test error handling scenarios"""
     
     @pytest.mark.asyncio
-    @patch('gemini_server.genai.GenerativeModel')
+    @patch('google.generativeai.GenerativeModel')
     async def test_handle_call_tool_chat_api_error(self, mock_model):
         """Test handling API errors in chat"""
         mock_instance = Mock()
@@ -253,7 +282,7 @@ class TestErrorHandling:
         assert "API Error" in result[0].text
     
     @pytest.mark.asyncio
-    @patch('gemini_server.genai.GenerativeModel')
+    @patch('google.generativeai.GenerativeModel')
     async def test_handle_call_tool_chat_blocked_response(self, mock_model):
         """Test handling blocked responses"""
         mock_response = Mock()