Skip to main content
Glama

Dev MCP Prompt Server

by LeonNonnast
npmGitHub
JavaScript
MIT License
1
OverviewInspectNewEndpointsSchemaRelated ServersReviewsScore
Need Help?View Source CodeReport Issue

MCP DevPrompts

npm version License: MIT TypeScript Model Context Protocol

Curated AI prompts for developers, delivered through the Model Context Protocol

A lightweight MCP server providing battle-tested prompts for AI-powered development workflows. Create specialized agents by combining modular skills, or use expert AI profiles for debugging, SQL optimization, and more.

🚀 Quick Start

Installation

git clone https://github.com/LeonNonnast/mcpdevprompts cd mcpdevprompts npm install npm run build claude mcp add mcpdevprompts --node /path/to/mcpdevprompts/build/server.js

Usage with Claude

# Use prompts directly claude prompt debug-andy "My API returns 500 errors randomly" claude prompt sql-expert "Optimize this slow query" claude prompt clean-code-clarity-readability "Create a user service with clean code"

Quick Workflow Examples

🔍 Discover Available Profiles & Skills

# See all available AI profiles claude search_profiles # Returns: debug-andy, sql-expert, performance-kai, lovable-ai-editor-base, etc. # List all development skills claude list_skills # Returns: clean-code-clarity-readability, testing-strategies, error-handling-best-practices, etc.

👥 Work with AI Profiles

# Use a specialized debugging expert claude prompt debug-andy "My React app crashes randomly on mobile devices" # Get SQL optimization help claude prompt sql-expert "This query takes 30 seconds, how can I optimize it?" # Performance analysis claude prompt performance-kai "My Node.js API response time increased by 200%"

🧠 Load Skills into Your Agent

# Load clean code skills claude load_skills '{ "skill_ids": ["clean-code-clarity-readability", "clean-code-small-functions"], "agent_name": "Clean Code Assistant" }' # Load testing expertise claude load_skills '{ "skill_ids": ["testing-strategies", "error-handling-best-practices"], "agent_name": "Testing Expert" }' # Create a full-stack quality agent claude load_skills '{ "skill_ids": ["clean-code-clarity-readability", "clean-code-small-functions", "testing-strategies"], "agent_name": "Full-Stack Expert" }'

🎯 Real-World Scenarios

Scenario 1: Debugging Session

# 1. Start with debugging expert claude prompt debug-andy "API endpoint returns 500 error intermittently" # 2. Load additional skills for comprehensive solution claude load_skills '{ "skill_ids": ["error-handling-best-practices", "testing-strategies"], "agent_name": "Debug & Test Expert" }' # 3. Now ask for complete solution "Create robust error handling and tests for this API endpoint"

Scenario 2: Code Quality Review

# 1. Load clean code skills claude load_skills '{ "skill_ids": ["clean-code-clarity-readability", "clean-code-small-functions", "clean-code-commenting"], "agent_name": "Code Quality Reviewer" }' # 2. Review and improve code "Review this function and suggest improvements following clean code principles"

Scenario 3: Onboard New AI Agent

# 1. Onboard a specialized editor claude prompt project-onboarding "Introduce lovable-ai-editor-base for code refactoring tasks" # 2. Combine with additional skills claude load_skills '{ "skill_ids": ["clean-code-clarity-readability", "testing-strategies"], "agent_name": "Enhanced Code Editor" }'

Local Development Testing

# Clone and test locally git clone https://github.com/mcpdevprompts.git cd server npm install npm run build npm run inspector # Opens MCP Inspector for testing

📚 Available Prompts

👥 AI Profiles

Expert AI assistants for specialized tasks:

  • debug-andy: Systematic debugging with root cause analysis

  • sql-expert: Advanced SQL query optimization and database design

  • performance-kai: Performance analysis and optimization strategies

  • lovable-ai-editor-base: AI-powered code editing and refactoring

  • perplexity-search-assistant: Research and information gathering

  • replit-expert-software-developer-editor: Full-stack development guidance

🛠️ Skills & Techniques

Development skills and methodologies:

  • project-onboarding: Introduce specialized AI agents to your workflow

  • clean-code-clarity-readability: Generate clear, self-explanatory code

  • clean-code-small-functions: Write focused, single-purpose functions

  • clean-code-commenting: Add meaningful comments and documentation

  • error-handling-best-practices: Implement robust error handling

  • testing-strategies: Create comprehensive test suites

🎯 Specialized Tools

Built-in tools for enhanced functionality:

  • search_prompts: Find prompts by keyword or category

  • search_profiles: Find AI profiles by specialization

  • get_prompt_stats: View prompt collection statistics

  • get_tool_stats: View available tools and usage

  • list_skills: List all available development skills

  • load_skills: Load multiple skills into an agent's knowledge base

Tool Examples:

# Search for profiles claude search_profiles # Returns: debug-andy, sql-expert, performance-kai, etc. # List all available skills claude list_skills # Returns: clean-code-clarity-readability, testing-strategies, etc. # Load multiple skills into an agent claude load_skills '{"skill_ids": ["clean-code-clarity-readability", "testing-strategies"], "agent_name": "Clean Code Expert"}' # Returns: Agent loaded with specified skills and ready to use them # Get collection statistics claude get_prompt_stats # Returns: total prompts, categories, effectiveness ratings

💡 Use Cases

For Frontend Developers

# Get clean code generation claude prompt clean-code-clarity-readability "Create a React component for user profile" # Small, focused functions claude prompt clean-code-small-functions "Refactor this large function into smaller parts" # Add proper documentation claude prompt clean-code-commenting "Add documentation to this API endpoint"

For Backend Developers

# Database optimization claude prompt sql-expert "Optimize this N+1 query problem" # Performance debugging claude prompt performance-kai "My Node.js API is slow under load" # Systematic debugging claude prompt debug-andy "Random 500 errors in production"

For Team Leads

# Agent onboarding claude prompt project-onboarding "Introduce lovable-ai-editor profile for code review" # Error handling standards claude prompt error-handling-best-practices "Establish error handling guidelines" # Testing strategies claude prompt testing-strategies "Create testing plan for new microservice"

For Code Quality & Skill Management

# Clean code generation claude prompt clean-code-clarity-readability "Create a user authentication service" # Create a specialized agent with multiple skills claude list_skills # First see all available skills claude load_skills '{"skill_ids": ["clean-code-clarity-readability", "clean-code-small-functions", "testing-strategies"], "agent_name": "Code Quality Expert"}' # Now the agent has all three skills loaded and ready to use

🎪 Skill Management System

Available Skills

Our skill system provides modular development expertise that can be combined into specialized agents:

Clean Code Skills:

  • clean-code-clarity-readability: Generate self-explanatory code with meaningful names

  • clean-code-small-functions: Write focused, single-responsibility functions

  • clean-code-commenting: Add meaningful comments and documentation

Development Skills:

  • testing-strategies: Create comprehensive test suites and testing plans

  • error-handling-best-practices: Implement robust error handling patterns

  • project-onboarding: Guide specialized AI agents into workflow integration

Skill Workflow

1. Discover Available Skills

claude list_skills

Returns:

[ { "id": "clean-code-clarity-readability", "title": "Generate Clear and Readable Code", "description": "Generate self-explanatory code with meaningful names", "tags": ["clean code", "readability", "maintainability"], "effectiveness": 5 }, { "id": "clean-code-small-functions", "title": "Generate Small, Single-Responsibility Functions", "description": "Write focused, single-purpose functions under 20 lines", "tags": ["clean code", "functions", "modularity"], "effectiveness": 5 } ]

2. Load Skills into Agent

claude load_skills '{ "skill_ids": ["clean-code-clarity-readability", "clean-code-small-functions", "testing-strategies"], "agent_name": "Clean Code Expert" }'

Returns:

You are now a Clean Code Expert with the following specialized skills: [Combined skill prompts...] You have been equipped with these 3 specialized skills: - Generate Clear and Readable Code: Generate self-explanatory code with meaningful names - Generate Small, Single-Responsibility Functions: Write focused, single-purpose functions - Create Comprehensive Test Suites: Design testing strategies and test plans Please acknowledge that you have integrated these skills and are ready to apply them.

3. Use Your Specialized Agent

After loading skills, your agent automatically applies them to relevant requests:

# Agent now combines all loaded skills "Create a user authentication service with clean code and tests" # → Uses clean code + testing skills together

Pre-Built Skill Combinations

🧹 Clean Code Expert

claude load_skills '{ "skill_ids": ["clean-code-clarity-readability", "clean-code-small-functions", "clean-code-commenting"], "agent_name": "Clean Code Expert" }'

🧪 Testing Specialist

claude load_skills '{ "skill_ids": ["testing-strategies", "error-handling-best-practices"], "agent_name": "Testing Specialist" }'

🎯 Full-Stack Quality Agent

claude load_skills '{ "skill_ids": ["clean-code-clarity-readability", "clean-code-small-functions", "testing-strategies", "error-handling-best-practices"], "agent_name": "Full-Stack Quality Agent" }'

Benefits of Skill Management

  • 🔧 Modular: Mix and match skills for specific needs

  • 📈 Scalable: New skills integrate seamlessly

  • 👥 Collaborative: Share skill combinations with your team

  • 🎯 Focused: Create highly specialized agents for specific tasks

  • 💡 Intelligent: Skills work together contextually

🏗️ Architecture

mcpdevprompts/ ├── src/ # TypeScript source code │ ├── server.ts # Main MCP server │ ├── prompt-manager.ts # Prompt loading and management │ ├── tool-manager.ts # Tool management system │ └── utils/ ├── public/ │ ├── prompts/ │ │ ├── profiles/ # AI assistant profiles │ │ ├── skills/ # Development skills & techniques │ │ └── onboarding/ # Project & team setup │ ├── tools/ # MCP tools definitions │ └── schema/ # JSON schemas for validation ├── build/ # Compiled JavaScript └── docs/ # Documentation

🔧 Development

Prerequisites

  • Node.js 18.0.0 or higher

  • npm or yarn

Setup

# Clone the repository git clone https://github.com/mcpdevprompts/server.git cd server # Install dependencies npm install # Build the project npm run build # Run in development mode npm run dev # Test with MCP Inspector npm run inspector

Adding New Prompts

  1. Choose the right category:

    • profiles/ - AI assistant personalities

    • skills/ - Development techniques

    • onboarding/ - Setup and integration

  2. Follow the schema (see public/schema/prompt-schema.json):

    { "id": "unique-prompt-id", "title": "Human-readable title", "description": "What this prompt does", "category": "profiles|skills|onboarding", "tags": ["relevant", "searchable", "tags"], "prompt": "Your detailed prompt text here...", "examples": [ { "input": "Example input", "output": "Expected output description" } ], "effectiveness": 4.5, "author": "Your Name", "version": "1.0.0", "created_at": "2024-01-01T00:00:00Z", "updated_at": "2024-01-01T00:00:00Z" }

  3. Test thoroughly with various inputs

  4. Submit a pull request with clear description

Adding New Tools

Tools extend the MCP server functionality with custom operations. Follow these steps:

  1. Choose a meaningful tool name (e.g., analyze_code, generate_tests, check_dependencies)

  2. Create the tool definition in public/tools/your-tool.json:

    { "id": "analyze_code_complexity", "name": "analyze_code_complexity", "description": "Analyze code complexity and suggest improvements", "input_schema": { "type": "object", "properties": { "code": { "type": "string", "description": "The code to analyze" }, "language": { "type": "string", "description": "Programming language (js, ts, py, etc.)" }, "metrics": { "type": "array", "items": { "type": "string" }, "description": "Metrics to calculate (cyclomatic, cognitive, etc.)" } }, "required": ["code", "language"] } }

  3. Implement the tool logic in src/server.ts CallToolRequestSchema handler:

    case "analyze_code_complexity": if (!args || typeof args.code !== "string") { throw new McpError(ErrorCode.InvalidRequest, "Code parameter is required"); } const analysis = await this.analyzeCodeComplexity(args.code, args.language); return { content: [ { type: "text", text: JSON.stringify(analysis, null, 2) } ] };

  4. Test the tool with MCP Inspector and various inputs

Tool Ideas:

  • validate_env_vars: Check environment variable completeness

  • generate_tests: Create unit tests for given code

  • check_dependencies: Analyze package.json for vulnerabilities

  • format_sql: Format and validate SQL queries

  • analyze_performance: Detect performance bottlenecks

  • generate_docs: Create documentation from code comments

📊 Quality Standards

All prompts must meet these criteria:

  • Effectiveness: Average rating of 4.0+ from community testing

  • Clarity: Clear, actionable instructions

  • Completeness: Comprehensive coverage of the task

  • Best Practices: Follow current industry standards

  • Accessibility: Consider accessibility requirements where applicable

🤝 Contributing

We welcome contributions! Please see our Contributing Guide for details.

Types of Contributions

  • New Prompts: Add high-quality prompts for common development tasks

  • Prompt Improvements: Enhance existing prompts based on user feedback

  • Documentation: Improve setup guides and usage examples

  • Bug Fixes: Report and fix issues with the server

  • Tools: Add new MCP tools for enhanced functionality

🔒 Security

  • No sensitive data in prompts

  • Input validation for all user inputs

  • Rate limiting on API endpoints

  • Regular security audits

  • Schema validation for all prompts and tools

🎯 Roadmap

  • Phase 1: TypeScript MCP server with core prompts

  • Phase 2: AI profiles and specialized tools

  • Phase 3: Skill management system with combinable expertise

  • Phase 4: Community contributions and rating system

  • Phase 5: IDE integrations and advanced analytics

  • Phase 6: Custom prompt collections and enterprise features

📝 License

MIT License - see LICENSE for details.

🙏 Acknowledgments

📞 Support

Made with ❤️ by the MCP DevPrompts community

Deploy Server
A
security – no known vulnerabilities
A
license - permissive license
A
quality - confirmed to work

How are these scores calculated?

remote-capable server

The server can be hosted and run remotely because it primarily relies on remote services or has no dependency on the local environment.

Tools

A lightweight server that provides curated, high-quality prompts for common development tasks like UI/UX design, project setup, and debugging to enhance AI-powered development workflows.

  1. 🚀 Quick Start
    1. Installation
    2. Usage with Claude
    3. Quick Workflow Examples
    4. Local Development Testing
  2. 📚 Available Prompts
    1. 👥 AI Profiles
    2. 🛠️ Skills & Techniques
    3. 🎯 Specialized Tools
  3. 💡 Use Cases
    1. For Frontend Developers
    2. For Backend Developers
    3. For Team Leads
    4. For Code Quality & Skill Management
  4. 🎪 Skill Management System
    1. Available Skills
    2. Skill Workflow
    3. Pre-Built Skill Combinations
    4. Benefits of Skill Management
  5. 🏗️ Architecture
    1. 🔧 Development
      1. Prerequisites
      2. Setup
      3. Adding New Prompts
      4. Adding New Tools
    2. 📊 Quality Standards
      1. 🤝 Contributing
        1. Types of Contributions
      2. 🔒 Security
        1. 🎯 Roadmap
          1. 📝 License
            1. 🙏 Acknowledgments
              1. 📞 Support

                Related MCP Servers

                • TypeScript Prompt MCP Server

                  gpaul-mcp
                  A
                  security
                  A
                  license
                  A
                  quality
                  Provides pre-defined prompt templates for AI assistants to generate comprehensive plans for TypeScript projects, API architectures, and GitHub workflows.
                  Last updated -
                  4
                  2
                  MIT License

                • PromptLab MCP Server

                  iRahulPandey
                  -
                  security
                  A
                  license
                  -
                  quality
                  Serves prompt templates through a standardized protocol for transforming basic user queries into optimized prompts for AI systems.
                  Last updated -
                  6
                  Apache 2.0

                • Hi-AI

                  su-record
                  A
                  security
                  F
                  license
                  A
                  quality
                  A simple AI development tool that helps users interact with AI through natural language commands, offering 29 tools across thinking, memory, browser, code quality, planning, and time management capabilities.
                  Last updated -
                  33
                  6
                  1

                • Context Engineering MCP Platform

                  ShunsukeHayashi
                  -
                  security
                  A
                  license
                  -
                  quality
                  A development platform that helps AI developers optimize prompts through intelligent context management, providing tools for analysis, optimization, and template management to reduce costs and improve AI response quality.
                  Last updated -
                  24
                  MIT License

                View all related MCP servers

                Appeared in Searches

                New MCP Servers

                MCP directory API

                We provide all the information about MCP servers via our MCP API.

                curl -X GET 'https://glama.ai/api/mcp/v1/servers/LeonNonnast/mcpdevprompts'

                If you have feedback or need assistance with the MCP directory API, please join our Discord server