mcp-agentic-sdlc
A comprehensive framework for managing software development lifecycle with AI agents, combining structured development processes with intelligent workflow management.
claude mcp add --transport stdio michaelwybraniec-mcp-agentic-sdlc npx -y mcp-agentic-sdlc \ --env MCP_ENV="Describe environment variable placeholders if needed"
How to use
This MCP server provides an Agentic Software Development Lifecycle (ASDLC) framework and an Agentic Workflow Protocol (AWP) to manage AI-human collaboration across software development lifecycles. It exposes a structured set of tools to guide project setup, generate recommendations, and create complete project structures with embedded documentation and tasks. Core capabilities include the base tool for interactive requirements gathering, the recommend tool to surface AI-driven suggestions, and the init tool to automatically scaffold the project with populated requirements, backlog, tech specs, and task folders. Use these tools to iteratively define your backlog, refine requirements, and instill standardized workflows that align with the ASDLC and AWP concepts. The server emphasizes context preservation, progress tracking, and documentation synchronization to support Scrum, Kanban, or other methodologies in an agentic, human-AI collaborative environment.
How to install
Prerequisites:
- Node.js (v14+ recommended) and npm installed on your machine
- Internet access to fetch the MCP package via npm/pnpm/yarn
Installation steps:
- Ensure you have Node.js and npm installed. Verify with: node -v npm -v
- Run the MCP server via npx (no global install required): npx -y mcp-agentic-sdlc
- If you prefer to install locally, you can install the package and run a local script (adjust as needed): npm install --save-dev mcp-agentic-sdlc npx mcp-agentic-sdlc
- If you intend to pin a specific version, replace the package name with the version, e.g.: npx -y mcp-agentic-sdlc@1.0.0
- For environments that require environment variables, create a .env file or export variables before running the command, e.g.: export MCP_ENV=production npx -y mcp-agentic-sdlc
Notes:
- The MCP server is designed to run with npx to avoid global installs; you can also install it locally if you prefer a project-scoped dependency.
Additional notes
Tips and common issues:
- If you encounter network restrictions, ensure your npm registry access is allowed or use a corporate proxy as needed.
- When running via npx, the package will be fetched from the npm registry each time unless cached; consider pinning a version for reproducibility.
- Review the generated documentation and task structures (base.md, requirements.md, backlog.md, tech-specs.md) after initialization to ensure alignment with your project goals.
- Environment variables (if any) should be documented in your deployment environment and loaded before the MCP server starts.
- The MCP server supports integration with Cursor and Claude Desktop via the example MCP config; adapt the configuration to your tooling stack if you’re using alternative clients.
Related MCP Servers
mcp-jfrog
Model Context Protocol (MCP) Server for the JFrog Platform API, enabling repository management, build tracking, release lifecycle management, and more.
furi
CLI & API for MCP management
sharedcontext
MCP server that gives AI coding assistants persistent cross-client memory. Facts and conversations stored in SQLite, encrypted with AES-256-GCM, synced to Arweave. No server, no account, recoverable with a 12-word phrase.
CodeRAG
Advanced graph-based code analysis for AI-assisted software development
context-engineering
Automated Context Engineering MCP Server for creating high-quality Product Requirements Prompts (PRPs) through AI-assisted workflows
mcp-demo
Example of using MCP Gateway with E2B sandboxes