Code-MCP
Turns AI assistants into full-stack software engineers with 36 tools for cognitive reasoning, code validation, project scaffolding, and AI/IDE configuration generation across 130+ programming languages, databases, and frameworks.
README
Code-MCP
🧠 The AI Coding Brain - A comprehensive MCP server that gives AI assistants superpowers
✨ What is Code-MCP?
Code-MCP is a Model Context Protocol (MCP) server that supercharges AI coding assistants like Claude, Cursor, and GitHub Copilot with 70 functional tools, 22 smart prompts, and 142+ resources.
🚀 Features
- 71 Functional Tools - Code generators, validators, helpers
- 22 Smart Prompts - Developer personas deeply integrated with Code-MCP tools
- 99 Code Templates - Production-ready examples
- 142+ Resources - Languages, frameworks, databases
📦 Installation
Local Installation (Recommended)
# Clone the repository
git clone https://github.com/millsydotdev/Code-MCP.git
cd Code-MCP
# Install dependencies
npm install
# Build the project
npm run build
# Test locally
npm start
NPX (Coming Soon)
npx code-mcp
⚡ Quick Start
1. Add to Claude Desktop
Edit your Claude Desktop config (%APPDATA%\Claude\claude_desktop_config.json on Windows or ~/Library/Application Support/Claude/claude_desktop_config.json on Mac):
{
"mcpServers": {
"code-mcp": {
"command": "node",
"args": ["C:/path/to/Code-MCP/dist/index.js"]
}
}
}
2. Add to Cursor
Add to your Cursor MCP settings:
{
"mcpServers": {
"code-mcp": {
"command": "node",
"args": ["/path/to/Code-MCP/dist/index.js"]
}
}
}
3. Restart your AI assistant and start using the tools!
🛠️ All 71 Tools
Cognitive Tools (10)
| Tool | Description |
|---|---|
sequential_thinking |
Step-by-step structured reasoning |
plan_task |
Create structured task plans |
reflect_on_code |
Code quality analysis |
analyze_architecture |
System design review |
debug_problem |
Systematic debugging approach |
brainstorm_solutions |
Generate solution approaches |
compare_approaches |
Compare technical options |
estimate_complexity |
Task complexity estimation |
generate_tests |
Test case generation |
explain_code |
Code explanation at any level |
Memory Tools (4)
| Tool | Description |
|---|---|
save_memory |
Persist key-value data |
read_memory |
Retrieve saved data |
list_memories |
List all memories |
clear_memory |
Clear memories |
Code Generators (6)
| Tool | Description |
|---|---|
generate_snippet |
Generate code for 12 patterns (React, Express, Prisma, etc.) |
regex_builder |
Build regex with explanations |
typescript_helper |
11 TypeScript patterns (interfaces, generics, etc.) |
generate_api_client |
Type-safe fetch/axios clients |
sql_helper |
12 SQL operations (queries, migrations, CTEs) |
validate_code |
Syntax validation |
Validation Tools (3)
| Tool | Description |
|---|---|
check_imports |
Check import statements |
lint_code |
Code linting |
format_code |
Code formatting |
File Generators (8)
| Tool | Description |
|---|---|
generate_package_json |
Complete package.json for 6 project types |
generate_dockerfile |
Optimized Dockerfiles (Node, Python, Go, Rust) |
generate_env_template |
Environment variable templates |
generate_readme |
Complete README.md files |
generate_license |
License files (MIT, Apache, GPL, etc.) |
generate_documentation |
Complete project documentation (API, Arch) |
generate_dashboard |
HTML Project Dashboard |
git_helper |
Git commands for 12 scenarios |
Advanced Tools (6)
| Tool | Description |
|---|---|
typescript_helper |
11 TypeScript patterns (interfaces, generics, etc.) |
generate_api_client |
Type-safe fetch/axios clients |
sql_helper |
12 SQL operations (queries, migrations, CTEs) |
graph_db_helper |
Graph DB queries (Cypher) for common operations |
generate_readme |
Complete README.md files |
generate_license |
License files (MIT, Apache, GPL, etc.) |
AI Config Generators (7)
| Tool | Description |
|---|---|
generate_cursor_rules |
.cursorrules file |
generate_claude_config |
CLAUDE.md file |
generate_gemini_config |
GEMINI.md file |
generate_copilot_config |
GitHub Copilot instructions |
generate_windsurf_config |
Windsurf rules |
generate_aider_config |
Aider configuration |
generate_cline_config |
Cline/Roo Code rules |
IDE Config Generators (5)
| Tool | Description |
|---|---|
generate_continue_config |
Continue.dev config |
generate_tabnine_config |
Tabnine config |
generate_vscode_tasks |
VSCode tasks.json |
generate_vscode_launch |
VSCode launch.json |
generate_jetbrains_config |
JetBrains run configs |
Full-Stack Tools (5)
| Tool | Description |
|---|---|
track_project |
Project structure analysis |
check_dependencies |
Dependency health check |
generate_github_actions |
CI/CD workflows |
full_stack_scaffold |
Complete project scaffold |
developer_rules |
Best practices checklist |
enforce_project_standards |
Enforce standards |
💡 Recommended Workflows
Combine tools for maximum effect:
1. New Feature Implementation
plan_task → sequential_thinking → generate_snippet → generate_tests
2. Refactoring Legacy Code
project_profiler → analyze_complexity → reflect_on_code → generate_tests
3. Systematic Debugging
debug_problem → read_file_snippet → search_files → explain_code
4. Project Setup
track_project → full_stack_scaffold → generate_readme → generate_github_actions
5. Documentation Update
track_project → summarize_files → generate_documentation → generate_dashboard
6. Agentic CI/CD (Self-Healing)
check_dependencies → security_scan → analyze_complexity → generate_pr_description
💬 22 Smart Prompts
| Prompt | Description |
|---|---|
setup_project |
Initialize a new project |
act_as_architect |
System design perspective |
act_as_debugger |
Systematic debugging |
act_as_reviewer |
Code review mindset |
act_as_security_auditor |
Security analysis |
act_as_mentor |
Teaching approach |
act_as_devops |
DevOps/SRE perspective |
act_as_tester |
Testing mindset |
act_as_optimizer |
Performance focus |
write_example_code |
Generate examples |
act_as_backend_dev |
Backend development |
act_as_frontend_dev |
Frontend development |
act_as_data_engineer |
Data pipelines |
act_as_mobile_dev |
Mobile development |
act_as_sre |
Site reliability |
act_as_api_designer |
API design |
act_as_dba |
Database administration |
act_as_tech_writer |
Documentation |
act_as_teacher |
Explain concepts |
act_as_pair_programmer |
Collaborative coding |
📚 Resources
Code-MCP includes comprehensive registries for:
- Languages - 55+ programming languages with paradigms and extensions
- Frameworks - 50+ frameworks (React, Vue, Django, FastAPI, etc.)
- Databases - 20+ databases (PostgreSQL, MongoDB, Redis, etc.)
- Cloud Providers - AWS, GCP, Azure, Vercel, Railway, etc.
- APIs - Discord, Stripe, OpenAI, Twilio integrations
- Game Engines - Unreal, Unity, Godot, Phaser, Bevy
- UI Frameworks - Tauri, Electron, HTMX, Alpine.js
🧪 Testing Locally
# Build the project
npm run build
# Run tests
npm test
# Build Docker image
docker build -t code-mcp .
# Run the server (uses stdio transport)
npm start
# Or run in development mode
npm run dev
📖 Example Usage
Once connected, ask your AI:
Use generate_snippet to create a React component called UserCard
Use git_helper to show me how to squash the last 3 commits
Use typescript_helper to generate a discriminated union for API responses
Use sql_helper to create a migration for a posts table
🤝 Contributing
Contributions welcome! See CONTRIBUTING.md for guidelines.
📄 License
MIT License - see LICENSE for details.
🔗 Links
Made with ❤️ by @millsydotdev
推荐服务器
Baidu Map
百度地图核心API现已全面兼容MCP协议,是国内首家兼容MCP协议的地图服务商。
Playwright MCP Server
一个模型上下文协议服务器,它使大型语言模型能够通过结构化的可访问性快照与网页进行交互,而无需视觉模型或屏幕截图。
Magic Component Platform (MCP)
一个由人工智能驱动的工具,可以从自然语言描述生成现代化的用户界面组件,并与流行的集成开发环境(IDE)集成,从而简化用户界面开发流程。
Audiense Insights MCP Server
通过模型上下文协议启用与 Audiense Insights 账户的交互,从而促进营销洞察和受众数据的提取和分析,包括人口统计信息、行为和影响者互动。
VeyraX
一个单一的 MCP 工具,连接你所有喜爱的工具:Gmail、日历以及其他 40 多个工具。
graphlit-mcp-server
模型上下文协议 (MCP) 服务器实现了 MCP 客户端与 Graphlit 服务之间的集成。 除了网络爬取之外,还可以将任何内容(从 Slack 到 Gmail 再到播客订阅源)导入到 Graphlit 项目中,然后从 MCP 客户端检索相关内容。
Kagi MCP Server
一个 MCP 服务器,集成了 Kagi 搜索功能和 Claude AI,使 Claude 能够在回答需要最新信息的问题时执行实时网络搜索。
e2b-mcp-server
使用 MCP 通过 e2b 运行代码。
Neon MCP Server
用于与 Neon 管理 API 和数据库交互的 MCP 服务器
Exa MCP Server
模型上下文协议(MCP)服务器允许像 Claude 这样的 AI 助手使用 Exa AI 搜索 API 进行网络搜索。这种设置允许 AI 模型以安全和受控的方式获取实时的网络信息。