MCP s-for-Full-Stack-Development
A comprehensive collection of Model Context Protocol (MCP) servers designed to supercharge your development workflow with Claude Desktop. These servers enable Claude to interact with your databases, Git repositories, APIs, Docker containers, and development tools.
claude mcp add --transport stdio iamqasimali-mcp-servers-for-full-stack-development node /absolute/path/to/git-server.js
How to use
This MCP server bundle provides five integrated Claude tools to enhance full-stack development workflows. The Filesystem server lets Claude read, write, and navigate your codebase; the Database server enables executing SQL queries, inspecting schemas and statistics, and generating migrations for PostgreSQL and MySQL; the Git server gives Claude quick access to repository status, history, diffs, branches, and automated commit messages; the API Testing server enables crafting HTTP requests, running tests, generating test cases, performing load tests, and validating responses; and the DevTools server offers Docker container management, log access, command execution inside containers, and npm script inspection. To use them, ensure Claude Desktop is configured to point at each server’s executable and that any required environment variables (like database credentials) are provided. Invoke Claude with natural language prompts matching the available tool names (e.g., read_file, execute_query, git_status, http_request, docker_ps) to perform operations directly from your editor or IDE.
How to install
Prerequisites:
- Node.js v18 or higher installed on your machine
- Claude Desktop application installed
- Docker installed if you plan to use the DevTools server (optional)
- Access credentials for PostgreSQL/MySQL if you intend to use the Database server
Quick Setup:
# Clone the repository (replace with your actual URL)
git clone https://github.com/yourusername/mcp-servers.git
cd mcp-servers
# Install dependencies
npm install
# Run the setup script (if provided in repository)
chmod +x setup.sh
./setup.sh
Manual Setup:
- Install Dependencies
npm install
- Configure Claude Desktop Create or edit the Claude Desktop configuration file at:
- macOS: ~/Library/Application Support/Claude/claude_desktop_config.json
- Windows: %APPDATA%/Claude/claude_desktop_config.json
Example claude_desktop_config.json segment:
{
"mcpServers": {
"filesystem": {
"command": "node",
"args": ["/absolute/path/to/server.js"]
},
"database": {
"command": "node",
"args": ["/absolute/path/to/database-server.js"],
"env": {
"PG_HOST": "localhost",
"PG_PORT": "5432",
"PG_DATABASE": "your_database",
"PG_USER": "your_user",
"PG_PASSWORD": "your_password"
}
},
"git": {
"command": "node",
"args": ["/absolute/path/to/git-server.js"]
},
"api-testing": {
"command": "node",
"args": ["/absolute/path/to/api-testing-server.js"]
},
"devtools": {
"command": "node",
"args": ["/absolute/path/to/devtools-server.js"]
}
}
}
- Restart Claude Desktop
Additional notes
Tips:
- Use absolute paths for all server.js scripts to avoid path resolution issues.
- Keep environment variables in the Claude config per server, especially database credentials and Docker-related settings.
- If you modify tooling or add custom tools, ensure you update both ListTools and CallTool handlers as demonstrated in the documentation.
- For the DevTools server, ensure Docker is installed and the user has permissions to run docker commands without sudo where appropriate.
- Review Claude Desktop logs if a server fails to connect; common issues include incompatible Node versions, misconfigured paths, or missing environment variables.
- When testing locally, you can start each server individually with node server.js (or the appropriate entry script) to verify basic responsiveness before integrating through Claude.
- Back up your claude_desktop_config.json before making changes.
Related MCP Servers
mcp-neo4j
Neo4j Labs Model Context Protocol servers
Gitingest
mcp server for gitingest
mem0
✨ mem0 MCP Server: A memory system using mem0 for AI applications with model context protocl (MCP) integration. Enables long-term memory for AI agents as a drop-in MCP server.
github-brain
An experimental GitHub MCP server with local database.
time
⏰ Time MCP Server: Giving LLMs Time Awareness Capabilities
github-repo
Model Context Protocol server for Github Repo // Reading Github Repo