Claude Code Starter Kit MCP
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@Claude Code Starter Kit MCP run a security scan on the project"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
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-mcpSetup 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 |
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| test-engineer agent |
| security-auditor agent |
| code-reviewer agent |
| 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 v0.2.0Requires a PyPI Trusted Publisher configured for the pypi environment in your repository settings.
Related MCP server: Claude Flow MCP
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 issuesš 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 integrationš§ Available Commands
Testing Commands
Command | Description | Example |
| Generate tests for a file |
|
| Test all changed files |
|
| Analyze and improve coverage |
|
Security Commands
Command | Description | Example |
| Full security audit |
|
| Check dependencies only |
|
| Auto-fix vulnerabilities |
|
Code Quality Commands
Command | Description | Example |
| Review staged changes |
|
| Review specific file |
|
| Detect and fix issues |
|
| Safe refactoring |
|
Documentation Commands
Command | Description | Example |
| Generate/update docs |
|
| Document specific file |
|
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
# 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# 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# Add to your CLAUDE.md
## Testing
- Framework: testing + testify
- Run: `go test ./...`
- Coverage: `go test -coverprofile=coverage.out ./...`
## Style
- Formatter: gofmt, goimports
- Linter: golangci-lintš¤ 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!
Available Tools
12 toolsagent_bug_hunterC
Expert at detecting bugs, anti-patterns, and potential issues
Inputs: arguments.
agent_code_reviewerC
Expert code reviewer for quality and maintainability
Inputs: arguments.
agent_security_auditorD
Security expert for vulnerability detection and remediation
Inputs: arguments.
agent_test_engineerC
Specialized agent for comprehensive test generation
Inputs: arguments.
command_detailed_reviewB
Structured code review with checklist and severity ratings
Inputs: arguments.
command_docsC
Generate or update documentation for code
Inputs: arguments.
command_fix_bugsC
Detect and fix common bugs, anti-patterns, and code issues
Inputs: arguments.
command_monitorC
Monitor repository health, track issues, and identify maintenance tasks
Inputs: arguments.
command_refactorB
Safely refactor code with test verification
Inputs: arguments.
command_security_checkC
Scan for security vulnerabilities in code and dependencies
Inputs: arguments.
command_testB
Generate comprehensive unit tests for files. Use /test or /test --changed
Inputs: arguments.
command_test_coverageC
Analyze test coverage and generate tests for uncovered code
Inputs: arguments.
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogā¦
TDQS
Scored across 12 tools
There is overlap between agent tools (e.g., agent_bug_hunter, agent_code_reviewer) and command tools (e.g., command_fix_bugs, command_detailed_review) that cover similar concerns. However, descriptions differentiate detection vs. action, so some ambiguity remains.
Tools follow two consistent prefixes ('agent_' and 'command_') and use snake_case throughout. While the pattern is clear, the split between role-based and action-based naming could be more uniform.
With 12 tools covering code review, bug detection, security, testing, documentation, refactoring, and monitoring, the count is well-scoped for a comprehensive code quality assistant.
The toolkit covers the full lifecycle of code quality: analysis (agents), fixes, tests, documentation, monitoring, and refactoring. No obvious gaps for its stated purpose.
Maintenance
Related MCP Connectors
Multi-brand AI code review for Claude: up to 12 reviewers and a judge, no install.
Scan websites and code for security, performance and SEO issues from your AI assistant.
Claude Code / MCP skills for the dev pipeline: discover, spec, design, build, ship, operate.
Run accessibility, contrast, and design token audits and file QA issues from your AI coding tool.
Related MCP Servers
- AlicenseNot gradedqualityDmaintenanceProvides semantic code intelligence to help users search, navigate, and analyze entire codebases using plain English. It enables Claude to perform architectural overviews, bug detection, and refactor suggestions through local semantic search and keyword indexing.MIT
- FlicenseNot gradedqualityFmaintenanceIntegrates with Claude Code to execute AI-powered code analysis and workflow automation, supporting pre-defined scenarios like code review and security audit.5-
- AlicenseAqualityDmaintenanceEnables real-time code analysis for JavaScript, TypeScript, and Python through Claude Desktop and other MCP clients, detecting bugs, code smells, and security vulnerabilities with automated quick fixes.7125 npm4MIT
- AlicenseNot gradedqualityDmaintenanceProvides security scanning tools for Claude Code, enabling real-time vulnerability detection, code analysis, and rule explanations for codebases.MIT