torbjorn/my-pal-mcp-server
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: resolve mypy type errors and linting issues

Browse Source 
- Add type annotation for server variable
- Fix handling of optional parameters in chat and analyze_code handlers
- Rename request variable to request_analysis to avoid type confusion
- Fix model listing to handle missing attributes safely
- Remove emoji icons from README section headers
- Fix flake8 formatting issues (whitespace, line length)

All tests passing, mypy and flake8 checks now pass in CI.

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

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Fahad
2025-06-08 21:25:19 +04:00
parent fe1fb83ab5
commit fb1d843950
2 changed files with 52 additions and 43 deletions
Download Patch File Download Diff File Expand all files Collapse all files

34
README.md
View File

@@ -2,7 +2,7 @@
A specialized Model Context Protocol (MCP) server that extends Claude Code's capabilities with Google's Gemini 2.5 Pro Preview, featuring a massive 1M token context window for handling large codebases and complex analysis tasks.
## 🎯 Purpose
## Purpose
This server acts as a developer assistant that augments Claude Code when you need:
- Analysis of files too large for Claude's context window
@@ -11,7 +11,7 @@ This server acts as a developer assistant that augments Claude Code when you nee
- Performance analysis of large codebases
- Security audits requiring full codebase context
## 📋 Prerequisites
## Prerequisites
Before you begin, ensure you have the following:
@@ -21,7 +21,7 @@ Before you begin, ensure you have the following:
- Ensure your key is enabled for the `gemini-2.5-pro-preview` model
4. **Git:** The `git` command-line tool for cloning the repository
## 🚀 Quick Start for Claude Code
## Quick Start for Claude Code
### 1. Clone the Repository
@@ -114,7 +114,7 @@ Just talk to Claude naturally:
- "Ask Gemini to review the architecture of these files..."
- "Have Gemini check this codebase for security issues..."
## 🔍 How It Works
## How It Works
This server acts as a local proxy between Claude Code and the Google Gemini API, following the Model Context Protocol (MCP):
@@ -127,7 +127,7 @@ This server acts as a local proxy between Claude Code and the Google Gemini API,
All processing and API communication happens locally from your machine. Your API key is never exposed to Anthropic.
## 💻 Developer-Optimized Features
## Developer-Optimized Features
### Automatic Developer Context
When no custom system prompt is provided, Gemini automatically operates with deep developer expertise, focusing on:
@@ -147,7 +147,7 @@ When no custom system prompt is provided, Gemini automatically operates with dee
- Perfect for analyzing entire codebases
- Maintains context across multiple large files
## 🛠️ Available Tools
## Available Tools
### `chat`
General-purpose developer conversations with Gemini.
@@ -170,7 +170,7 @@ Specialized tool for analyzing large files or multiple files that exceed Claude'
### `list_models`
Lists available Gemini models (defaults to 2.5 Pro Preview).
## 📋 Installation
## Installation
1. Clone the repository:
```bash
@@ -194,7 +194,7 @@ Lists available Gemini models (defaults to 2.5 Pro Preview).
export GEMINI_API_KEY="your-api-key-here"
```
## 🔧 Advanced Configuration
## Advanced Configuration
### Custom System Prompts
Override the default developer prompt when needed:
@@ -217,7 +217,7 @@ While defaulting to `gemini-2.5-pro-preview-06-05`, you can specify other models
- `gemini-1.5-flash`: Faster responses
- Use `list_models` to see all available options
## 🎯 Claude Code Integration Examples
## Claude Code Integration Examples
### When Claude hits token limits:
```
@@ -235,12 +235,12 @@ You: "Use Gemini to analyze all files in /src/core/ and create an architecture d
You: "Have Gemini profile this codebase and suggest the top 5 performance improvements"
```
## 💡 Practical Usage Tips
## Practical Usage Tips
### Effective Commands
Be specific about what you want from Gemini:
- ✅ "Ask Gemini to identify memory leaks in this code"
- ❌ "Ask Gemini about this"
- Good: "Ask Gemini to identify memory leaks in this code"
- Bad: "Ask Gemini about this"
### Common Workflows
@@ -308,14 +308,14 @@ You: "Have Gemini review my approach and check these 10 files for compatibility
6. Claude: [Refines design addressing all concerns]
```
## 📝 Notes
## Notes
- Gemini 2.5 Pro Preview may occasionally block certain prompts due to safety filters
- If a prompt is blocked by Google's safety filters, the server will return a clear error message to Claude explaining why the request could not be completed
- Token estimation: ~4 characters per token
- All file paths should be absolute paths
## 🔧 Troubleshooting
## Troubleshooting
### Server Not Appearing in Claude
@@ -337,7 +337,7 @@ You: "Have Gemini review my approach and check these 10 files for compatibility
- **`chmod: command not found` (Windows):** The `chmod +x` command is for macOS/Linux only. Windows users can skip this step
- **Path not found errors:** Use absolute paths in all configurations, not relative paths like `./run_gemini.sh`
## 🧪 Testing
## Testing
### Running Tests Locally
@@ -368,7 +368,7 @@ This project uses GitHub Actions for automated testing:
- Includes linting with flake8, black, isort, and mypy
- Maintains 80%+ code coverage
## 🤝 Contributing
## Contributing
This server is designed specifically for Claude Code users. Contributions that enhance the developer experience are welcome!
@@ -380,6 +380,6 @@ This server is designed specifically for Claude Code users. Contributions that e
6. Push to the branch (`git push origin feature/amazing-feature`)
7. Open a Pull Request
## 📄 License
## License
MIT License - feel free to customize for your development workflow.

61
gemini_server.py
View File

@@ -103,7 +103,7 @@ class CodeAnalysisRequest(BaseModel):
# Create the MCP server instance
server = Server("gemini-server")
server: Server = Server("gemini-server")
# Configure Gemini API
@@ -150,7 +150,7 @@ def prepare_code_context(
# Add file contents
if files:
summary_parts.append(f"📁 Analyzing {len(files)} file(s):")
summary_parts.append(f"Analyzing {len(files)} file(s):")
for file_path in files:
# Get file content for Gemini
file_content = read_file_content_for_gemini(file_path)
@@ -171,7 +171,7 @@ def prepare_code_context(
preview = "\n".join(preview_lines)
if len(preview) > 100:
preview = preview[:100] + "..."
summary_parts.append(f" 📄 {file_path} ({size:,} bytes)")
summary_parts.append(f" {file_path} ({size:,} bytes)")
if preview.strip():
summary_parts.append(f" Preview: {preview[:50]}...")
except Exception:
@@ -186,7 +186,7 @@ def prepare_code_context(
)
context_parts.append(formatted_code)
preview = code[:100] + "..." if len(code) > 100 else code
summary_parts.append(f"💻 Direct code provided ({len(code):,} characters)")
summary_parts.append(f"Direct code provided ({len(code):,} characters)")
summary_parts.append(f" Preview: {preview}")
full_context = "\n\n".join(context_parts)
@@ -302,11 +302,15 @@ async def handle_call_tool(name: str, arguments: Dict[str, Any]) -> List[TextCon
try:
# Use the specified model with optimized settings
model_name = request.model or DEFAULT_MODEL
temperature = request.temperature if request.temperature is not None else 0.5
max_tokens = request.max_tokens if request.max_tokens is not None else 8192
model = genai.GenerativeModel(
model_name=request.model,
model_name=model_name,
generation_config={
"temperature": request.temperature,
"max_output_tokens": request.max_tokens,
"temperature": temperature,
"max_output_tokens": max_tokens,
"candidate_count": 1,
},
)
@@ -342,10 +346,10 @@ async def handle_call_tool(name: str, arguments: Dict[str, Any]) -> List[TextCon
elif name == "analyze_code":
# Validate request
request = CodeAnalysisRequest(**arguments)
request_analysis = CodeAnalysisRequest(**arguments)
# Check that we have either files or code
if not request.files and not request.code:
if not request_analysis.files and not request_analysis.code:
return [
TextContent(
type="text",
@@ -355,7 +359,7 @@ async def handle_call_tool(name: str, arguments: Dict[str, Any]) -> List[TextCon
try:
# Prepare code context - always use non-verbose mode for Claude Code compatibility
code_context, summary = prepare_code_context(request.files, request.code)
code_context, summary = prepare_code_context(request_analysis.files, request_analysis.code)
# Count approximate tokens (rough estimate: 1 token ≈ 4 characters)
estimated_tokens = len(code_context) // 4
@@ -369,21 +373,25 @@ async def handle_call_tool(name: str, arguments: Dict[str, Any]) -> List[TextCon
]
# Use the specified model with optimized settings for code analysis
model_name = request_analysis.model or DEFAULT_MODEL
temperature = request_analysis.temperature if request_analysis.temperature is not None else 0.2
max_tokens = request_analysis.max_tokens if request_analysis.max_tokens is not None else 8192
model = genai.GenerativeModel(
model_name=request.model,
model_name=model_name,
generation_config={
"temperature": request.temperature,
"max_output_tokens": request.max_tokens,
"temperature": temperature,
"max_output_tokens": max_tokens,
"candidate_count": 1,
},
)
# Prepare the full prompt with enhanced developer context and clear structure
system_prompt = request.system_prompt or DEVELOPER_SYSTEM_PROMPT
system_prompt = request_analysis.system_prompt or DEVELOPER_SYSTEM_PROMPT
full_prompt = f"""{system_prompt}
=== USER REQUEST ===
{request.question}
{request_analysis.question}
=== END USER REQUEST ===
=== CODE TO ANALYZE ===
@@ -408,7 +416,7 @@ marked with their paths and content boundaries."""
text = f"Response blocked or incomplete. Finish reason: {finish_reason}"
# Always return response with summary for Claude Code compatibility
if request.files or request.code:
if request_analysis.files or request_analysis.code:
response_text = f"{summary}\n\n🤖 Gemini's Analysis:\n{text}"
else:
response_text = text
@@ -422,14 +430,15 @@ marked with their paths and content boundaries."""
try:
# List available models
models = []
for model in genai.list_models():
if "generateContent" in model.supported_generation_methods:
for model_info in genai.list_models():
if (hasattr(model_info, 'supported_generation_methods') and
"generateContent" in model_info.supported_generation_methods):
models.append(
{
"name": model.name,
"display_name": model.display_name,
"description": model.description,
"is_default": model.name == DEFAULT_MODEL,
"name": model_info.name,
"display_name": getattr(model_info, 'display_name', 'Unknown'),
"description": getattr(model_info, 'description', 'No description'),
"is_default": model_info.name.endswith(DEFAULT_MODEL),
}
)
@@ -458,10 +467,10 @@ Updated: {__updated__}
Author: {__author__}
Configuration:
• Default Model: {DEFAULT_MODEL}
• Max Context: {MAX_CONTEXT_TOKENS:,} tokens
• Python: {version_info['python_version']}
• Started: {version_info['server_started']}
- Default Model: {DEFAULT_MODEL}
- Max Context: {MAX_CONTEXT_TOKENS:,} tokens
- Python: {version_info['python_version']}
- Started: {version_info['server_started']}
For updates, visit: https://github.com/BeehiveInnovations/gemini-mcp-server""",
)