Claude Code Starter Kit MCP
Enables AI-powered automated testing, security scanning, code review, and maintenance tasks directly within Claude Code or desktop.
README
š¤ Claude Code Starter Kit
A production-ready boilerplate for integrating Claude Code into your development workflow. Automate testing, security scanning, code review, and routine maintenance tasks.
š¦ MCP Server
All commands and agents in this kit are also available as an MCP (Model Context Protocol) server, making them usable from Claude Desktop, Claude Code, or any MCP-compatible client.
Install
pip install claude-code-starter-kit-mcp
Setup in Claude Code
Add to your project's .claude/settings.json (or ~/.claude/settings.json for global use):
{
"mcpServers": {
"claude-code-starter-kit": {
"command": "claude-code-starter-kit-mcp"
}
}
}
Setup in Claude Desktop
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"claude-code-starter-kit": {
"command": "claude-code-starter-kit-mcp"
}
}
}
Available MCP Tools
| Tool | Maps to |
|---|---|
command_test |
/test |
command_test_coverage |
/test-coverage |
command_security_check |
/security-check |
command_detailed_review |
/detailed-review |
command_fix_bugs |
/fix-bugs |
command_refactor |
/refactor |
command_docs |
/docs |
command_monitor |
/monitor |
agent_test_engineer |
test-engineer agent |
agent_security_auditor |
security-auditor agent |
agent_code_reviewer |
code-reviewer agent |
agent_bug_hunter |
bug-hunter agent |
All tools accept an optional arguments string (e.g. a file path or flags like --changed).
PyPI Auto-publish
Releases to PyPI are automated via GitHub Actions. Push a version tag to trigger a publish:
git tag v0.2.0
git push origin v0.2.0
Requires a PyPI Trusted Publisher configured for the pypi environment in your repository settings.
šÆ What This Kit Provides
| Feature | Description |
|---|---|
| Automated Testing | Generate unit tests for new code automatically |
| Security Scanning | Track vulnerabilities and get fix suggestions |
| Code Review | AI-powered review on every PR |
| Bug Detection | Monitor repo for common issues and anti-patterns |
| Documentation | Auto-generate and update docs |
š Quick Start
1. Copy to Your Project
# Clone this repo
git clone https://github.com/dachivadachkoria/claude-code-starter-kit.git
# Copy the .claude directory to your project
cp -r claude-code-starter-kit/.claude your-project/
cp claude-code-starter-kit/CLAUDE.md your-project/
2. Customize CLAUDE.md
Edit CLAUDE.md in your project root to match your:
- Tech stack
- Testing conventions
- Code style
- Project structure
3. Start Using
cd your-project
claude
# Now use the commands:
/test src/myfile.py # Generate tests
/security-check # Check vulnerabilities
/detailed-review # Code review
/fix-bugs # Auto-fix common issues
š Repository Structure
.claude/
āāā settings.json # Claude Code configuration
āāā commands/ # Slash commands
ā āāā test.md # /test - Generate unit tests
ā āāā test-coverage.md # /test-coverage - Coverage analysis
ā āāā security-check.md # /security-check - Vulnerability check
ā āāā detailed-review.md # /detailed-review - Code review
ā āāā fix-bugs.md # /fix-bugs - Auto-fix issues
ā āāā docs.md # /docs - Generate documentation
ā āāā refactor.md # /refactor - Safe refactoring
āāā agents/ # Specialized AI agents
ā āāā test-engineer.md # Testing specialist
ā āāā security-auditor.md # Security expert
ā āāā code-reviewer.md # Review specialist
ā āāā bug-hunter.md # Bug detection expert
āāā knowledge-base/ # Project-specific guidelines
āāā testing-guide.md
āāā security-checklist.md
CLAUDE.md # Project context (customize this!)
.github/
āāā workflows/
āāā claude-review.yml # Optional: CI integration
š§ Available Commands
Testing Commands
| Command | Description | Example |
|---|---|---|
/test <file> |
Generate tests for a file | /test src/auth.py |
/test --changed |
Test all changed files | /test --changed |
/test-coverage |
Analyze and improve coverage | /test-coverage |
Security Commands
| Command | Description | Example |
|---|---|---|
/security-check |
Full security audit | /security-check |
/security-check --deps |
Check dependencies only | /security-check --deps |
/security-fix |
Auto-fix vulnerabilities | /security-fix |
Code Quality Commands
| Command | Description | Example |
|---|---|---|
/detailed-review |
Review staged changes | /detailed-review |
/detailed-review <file> |
Review specific file | /detailed-review src/api.py |
/fix-bugs |
Detect and fix issues | /fix-bugs |
/refactor <file> |
Safe refactoring | /refactor src/legacy.py |
Documentation Commands
| Command | Description | Example |
|---|---|---|
/docs |
Generate/update docs | /docs |
/docs <file> |
Document specific file | /docs src/utils.py |
š” Built-in Commands
Claude Code has excellent built-in commands you should know:
/security-review- AI-powered security scanning/review- Code review/init- Initialize project with CLAUDE.md/compact- Compress context when running low
š”ļø Safety Guidelines
What Claude Code CAN Do Safely
ā
Generate and run tests
ā
Analyze code for vulnerabilities
ā
Suggest fixes with explanations
ā
Create documentation
ā
Refactor with your approval
What Requires Your Review
ā ļø Any changes to authentication/authorization
ā ļø Database migrations
ā ļø Environment/config changes
ā ļø Dependency updates
ā ļø Production deployment scripts
Best Practices
- Review before commit - Always review generated code
- Use branches - Let Claude work on feature branches
- Incremental changes - Small, focused tasks work best
- Test first - Run tests before accepting changes
- Version control - Commit frequently, revert if needed
š Language-Specific Setup
<details> <summary><b>Python</b></summary>
# Add to your CLAUDE.md
## Testing
- Framework: pytest
- Run: `pytest tests/ -v`
- Coverage: `pytest --cov=src --cov-report=html`
## Style
- Formatter: black, isort
- Linter: ruff or flake8
- Types: mypy
</details>
<details> <summary><b>JavaScript/TypeScript</b></summary>
# Add to your CLAUDE.md
## Testing
- Framework: jest or vitest
- Run: `npm test`
- Coverage: `npm test -- --coverage`
## Style
- Formatter: prettier
- Linter: eslint
- Types: TypeScript strict mode
</details>
<details> <summary><b>Go</b></summary>
# Add to your CLAUDE.md
## Testing
- Framework: testing + testify
- Run: `go test ./...`
- Coverage: `go test -coverprofile=coverage.out ./...`
## Style
- Formatter: gofmt, goimports
- Linter: golangci-lint
</details>
š¤ Contributing
Contributions welcome! Please read CONTRIBUTING.md for guidelines.
Ideas for Contributions
- [ ] More language-specific templates
- [ ] Framework-specific commands (Django, React, etc.)
- [ ] CI/CD integration examples
- [ ] IDE extension recommendations
- [ ] Video tutorials
š Resources
š License
MIT License - feel free to use in personal and commercial projects.
Made with š¤ by the community, for the community
Star ā this repo if you find it useful!
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.