DevOps Practices - MCP Server

mcp-name: io.github.ai-4-devops/devops-practices
Purpose: Productivity framework for DevOps engineers using AI assistance (Claude Code) while working on PoCs.
Type: Model Context Protocol (MCP) Server for Claude Code
Version: 1.4.0
Status: π Officially Published in the MCP Registry (Published: February 18, 2026)
Published Versions:
- π¦ PyPI: v1.4.0 β Git tag v1.4.0 (
34ca572)
- π MCP Registry: v1.4.0 β Git tag v1.4.0 (
34ca572)
- π Latest Development: main branch (may include unreleased features)
Who is this for? DevOps engineers using Claude Code (VS Code plugin) for PoC development.
What it does: Provides structure (TRACKER, ISSUES, docs, SoPs) so you can focus on building without worrying about documentation overhead.
What it's NOT: Not a DevOps tutorial - it's a productivity framework for AI-assisted development.
Why This MCP Server?
Solves the CLAUDE.md Bloat Problem
Tired of maintaining massive CLAUDE.md files (1000+ lines) across multiple projects? This MCP centralizes reusable DevOps instructions for engineers working on multiple PoCs, eliminating repeated instructions across projects and folders.
The Problem:
- β Large CLAUDE.md files eat up context window
- β Same practices duplicated across every project
- β Reinventing TRACKER.md, ISSUES.md, docs, SoPs for every PoC
- β Inconsistent standards across projects
- β Context wasted on instructions instead of actual work
The Solution:
- β
Pre-built structure - Templates for TRACKER, ISSUES, docs, SoPs
- β
Focus on work - Not on "how should I document this?"
- β
Consistency - Same standards across all your PoCs
- β
Team alignment - Same patterns enable seamless collaboration and easy handovers across sessions, systems, and team members
- β
Faster startup - Copy template, start working
- β
Context saved - No bloated CLAUDE.md files
What you get (structure, not knowledge):
- π TRACKER.md template - Start tracking immediately, don't design tracking
- π ISSUES.md system - Start logging issues, don't setup Jira
- π Documentation standards - Start writing docs, don't debate structure
- π Runbook templates - Start documenting ops, don't create SoP formats
- π Session continuity - Start handoffs, don't design handoff protocols
When searching "devops" in the MCP Registry (as of February 2026), this is the only result. While other MCPs focus on:
- π§ Development tools (code generation, testing, debugging)
- π Data analysis (databases, APIs, analytics)
- π¨ Content creation (writing, design, media)
This MCP provides:
- ποΈ Configuration structure - How to organize configs per environment, generate new env configs from completed ones, create and validate SoPs
- π Documentation patterns - TRACKER, ISSUES, docs, runbook templates ready to copy
- π Operations templates - Session handoff, runbook formats, documentation standards
- π― Structured guidance - GG-SS organized practices for quick discovery
What makes it different:
- Prescriptive, not generative - Provides proven practices, not generated code
- Infrastructure-first - Built for ops teams, not developers
- Reusable patterns - Templates and standards across all your projects
- AI-native design - Organized for Claude to query and apply contextually
- R&D optimized - Accelerates proof-of-concept development and experimentation
Perfect for: DevOps engineers using Claude Code (VS Code plugin) to build PoCs and conduct R&D with AI assistance.
How It Works
No server management required:
- β
Auto-start: Spawns when Claude Code/Desktop starts
- β
Background: Runs silently while you work
- β
On-demand: Claude queries practices as needed
- β
Auto-stop: Shuts down when Claude closes
- β
Fallback: Access practices via GitHub/local if MCP unavailable (see Troubleshooting)
Configuration Options:
You can configure the MCP server globally (all projects) or per-project:
Option 1: Global Configuration (~/.claude.json)
{
"mcpServers": {
"devops-practices": {
"command": "python3",
"args": ["-u", "~/.mcp-servers/devops-practices/mcp-server.py"],
"env": {"PYTHONUNBUFFERED": "1"}
}
}
}
Option 2: Project-Level Configuration (.mcp.json in project root)
{
"mcpServers": {
"devops-practices": {
"command": "python3",
"args": ["-u", "~/.mcp-servers/devops-practices/mcp-server.py"],
"env": {"PYTHONUNBUFFERED": "1"}
}
}
}
Setup Steps:
- Install the MCP server (see Installation section below)
- Add configuration to
~/.claude.json (global) or .mcp.json (per-project)
- Restart Claude Code/Desktop
- MCP server runs automatically - no manual startup needed
Note: The -u flag and PYTHONUNBUFFERED ensure real-time logging for debugging.
What This Provides
This MCP server provides shared DevOps practices that are common across infrastructure projects:
Available Practices (11)
Organized using GG-SS prefix pattern (Group-Sequence) for better discoverability:
Naming Pattern: GG-SS-practice-name
- GG = Group ID (01-04) - Functional category
- SS = Sequence ID (01-03) - Order within group
- Example:
03-02-air-gapped-workflow = Group 03, Sequence 02
Group Legend:
- 01 = Workflow & Processes (how to work effectively)
- 02 = Version Control & Project Management (git, issues)
- 03 = Infrastructure & Configuration (K8s, deployments, config)
- 04 = Documentation Standards (docs, READMEs, runbooks)
Group 01: Workflow & Processes
- 01-01-session-continuity - State tracking, handoff protocols, CURRENT-STATE.md
- 01-02-task-tracking - TRACKER.md, CURRENT-STATE.md, PENDING-CHANGES.md
- 01-03-efficiency-guidelines - When to script vs copy-paste, batching commands
Group 02: Version Control & Project Management
- 02-01-git-practices - Using
git mv, commit conventions, backup protocols, GitLab Flow
- 02-02-issue-tracking π - In-repository Jira-like issue tracking system (Advanced)
Group 03: Infrastructure & Configuration
- 03-01-configuration-management β - Config organization, placeholders, environment isolation
- 03-02-air-gapped-workflow - Working across laptop, CloudShell, bastion, and EKS
- 03-03-standard-workflow - Common operational patterns and workflows
Group 04: Documentation Standards
- 04-01-documentation-standards - HOW/WHAT/WHY structure, naming conventions
- 04-02-readme-maintenance β - Directory documentation standards and best practices
- 04-03-runbook-documentation β - Mandatory session log standards and requirements
Available Templates (7)
- TRACKER.md - Task tracking template (milestones)
- CURRENT-STATE.md - Session handoff template
- CLAUDE.md - Simplified project instructions template
- RUNBOOK.md β - Session log template with all required sections
- ISSUE.md π - Individual issue template (Advanced)
- ISSUES.md π - Issue index template with stats dashboard (Advanced)
- issues/README.md π - How to use the issue system (Advanced)
Architecture
devops-practices-mcp/
βββ README.md # This file
βββ mcp-server.py # MCP server implementation
βββ requirements.txt # Python dependencies
βββ .github/workflows/ci.yml # GitHub Actions pipeline
βββ health-check.sh # Health validation script
βββ practices/ # Shared practice documents (11 files, GG-SS organized)
β βββ 01-01-session-continuity.md
β βββ 01-02-task-tracking.md
β βββ 01-03-efficiency-guidelines.md
β βββ 02-01-git-practices.md
β βββ 02-02-issue-tracking.md # π Advanced: In-repo issue tracking
β βββ 03-01-configuration-management.md
β βββ 03-02-air-gapped-workflow.md
β βββ 03-03-standard-workflow.md
β βββ 04-01-documentation-standards.md
β βββ 04-02-readme-maintenance.md
β βββ 04-03-runbook-documentation.md
βββ templates/ # File templates (7 files)
β βββ TRACKER-template.md
β βββ CURRENT-STATE-template.md
β βββ CLAUDE-template.md
β βββ RUNBOOK-template.md
β βββ ISSUE-TEMPLATE.md # π Individual issue template
β βββ ISSUES.md # π Issue index with dashboard
β βββ issues-README.md # π Issue system guide
βββ tools/ # Automation tools π
β βββ issue-manager.sh # CLI for managing issues
βββ config/ # MCP configuration
βββ mcp-config.json # Server configuration
MCP Tools
The MCP server provides 5 tools for Claude to query practices and templates: