Skip to main content
Glama

Structured Workflow Engine MCP Server

by mlaurel
MIT License

🎯 Structured Workflow Engine MCP Server

Context Engineering Framework with ready-to-use development workflows that bring structure to chaos.

🎯 What is this

Structured Workflow System - designed to help both high-tier and low-tier AI models follow consistent processes:

  • 🧠 Context Engineering - workflows engineered for reliable AI execution across model tiers

  • 🔧 9 Workflows - battle-tested processes that provide structure and guardrails

  • ⚡ Smart Validation - automatically validates prerequisites and skips irrelevant steps

  • 📋 12 Mini-Prompts - context-engineered prompts organized by development phases

🚀 Installation

# 1. Clone repository git clone https://github.com/your-repo/agents-playbook cd agents-playbook # 2. Install dependencies npm install # 3. Add OpenAI API key to .env OPENAI_API_KEY=your_key_here # 4. Generate search index npm run build:embeddings # 5. Start server npm run dev

MCP Server:

🧪 Testing

# MCP Inspector for testing DANGEROUSLY_OMIT_AUTH=true npx @modelcontextprotocol/inspector@latest http://localhost:3000/api/mcp # Run tests (90+ tests) npm run test:integration

🛠️ Available Tools

get_available_workflows

Search workflows with AI semantic search.

Example:

  • Input: "fix critical bug"

  • Output: quick-fix workflow (🎯 89% match)

select_workflow

Get complete workflow with execution plan.

get_next_step

Step-by-step navigation with smart validation.

📁 Workflows (9 total)

🚀 Development (4)

  • feature-development - Complete feature development lifecycle

  • product-development - From idea to product launch

  • quick-fix - Fast bug fixes and hotfixes

  • code-refactoring - Code architecture improvements

🧪 Testing & QA (3)

  • fix-tests - Systematic test failure diagnosis and repair with refactoring integration

  • fix-circular-dependencies - Comprehensive circular dependency resolution with architectural refactoring

  • unit-test-coverage - Comprehensive unit test coverage improvement

📋 Setup & Planning (2)

  • project-initialization - New project setup

  • trd-creation - Technical Requirements Document creation

🎯 Usage Examples

1. Search: "create new feature" 2. Result: feature-development workflow (🎯 92% match) 3. Execute: 14 steps with TRD integration and smart skipping
1. Search: "improve test coverage" 2. Result: unit-test-coverage workflow (🎯 94% match) 3. Execute: 7 steps of systematic coverage improvement
1. Search: "circular dependencies" 2. Result: fix-circular-dependencies workflow (🎯 95% match) 3. Execute: 7 steps of dependency resolution with refactoring integration
1. Search: "technical documentation" 2. Result: trd-creation workflow (🎯 94% match) 3. Execute: 7 steps of TRD creation with validation

🔌 MCP Integration

🤖 Claude Desktop

{ "mcpServers": { "agents-playbook": { "url": "https://agents-playbook.vercel.app/api/mcp" } } }

🎯 Cursor

Add to your Cursor settings or create a MCP configuration:

{ "mcpServers": { "agents-playbook": { "url": "https://agents-playbook.vercel.app/api/mcp", "description": "AI Agent Workflow Engine with semantic search" } } }

For Cursor users:

  1. Open Cursor Settings

  2. Navigate to "Extensions" or "Integrations"

  3. Add MCP Server configuration

  4. Restart Cursor

📁 Direct File Usage (Any IDE)

Copy playbook files directly to your project:

# Copy entire playbook to your project cp -r public/playbook/ /path/to/your/project/ # For Cursor: create a .cursorrules file echo "Use workflows from playbook/ directory for structured development" > .cursorrules

📚 Local Usage

# Copy entire playbook to your project cp -r public/playbook/ /path/to/your/project/ # For Cursor: create a .cursorrules file echo "Use workflows from playbook/ directory for structured development" > .cursorrules

Benefits:

  • ✅ Works without MCP server

  • ✅ Customize for your team

  • ✅ Offline access

  • ✅ Version control with project

  • ✅ Cursor can reference workflows directly

🧠 How it works

  • Context Engineering - workflows designed with clear context boundaries and validation

  • Semantic Search - OpenAI embeddings understand task context for workflow selection

  • YAML Workflows - structured processes with phases, steps, and guardrails

  • Mini-Prompts - context-engineered reusable prompts that work across model tiers

  • Smart Validation - prevents execution without required context, provides structure for low-tier models

🐛 Troubleshooting

"No workflows found"

  • Use simple terms: "bug", "feature", "documentation"

  • Check: npm run build:embeddings

"OpenAI API errors"

  • Check OPENAI_API_KEY in .env

  • System falls back to text search if OpenAI unavailable

"Can't connect to MCP server"

  • Make sure server is running: npm run dev

  • URL: http://localhost:3000/api/mcp

"Steps are being skipped"

  • This is normal behavior! System skips steps without required context

  • Check logs to understand skip reasons


🎯 Structured Workflow Engine - Context engineering framework that brings order to chaos in AI-driven development

Related MCP Servers

  • -
    security
    A
    license
    -
    quality
    A FastAPI-based implementation of the Model Context Protocol that enables standardized interaction between AI models and development environments, making it easier for developers to integrate and manage AI tasks.
    Last updated -
    10
    MIT License
  • A
    security
    F
    license
    A
    quality
    A powerful context management system that maintains persistent context across coding sessions, helping development teams track project structure, dependencies, and progress.
    Last updated -
    6
    5
    • Apple
    • Linux
  • -
    security
    F
    license
    -
    quality
    A server-side implementation that handles context processing between GitHub repositories and AI models, enabling seamless integration of AI capabilities with codebases through the Model Context Protocol.
    Last updated -
    1
  • A
    security
    A
    license
    A
    quality
    Provides intelligent context management for AI development sessions, allowing users to track token usage, manage conversation context, and seamlessly restore context when reaching token limits.
    Last updated -
    8
    0
    2
    Apache 2.0
    • Linux
    • Apple

View all related 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/mlaurel/mcp-workflow-engine'

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