ContextEngine MCP Server - Up-to-date documentation and code examples for any library
npm install context-engineA Model Context Protocol (MCP) server that provides an interface to the ContextEngine system - a comprehensive Documentation Driven Development (DDD) methodology. This MCP server enables AI assistants to access ContextEngine's structured workflows, context management tools, and knowledge graph system for documentation-first development processes, eliminating repetitive context provision and ensuring code generation follows documented requirements.
ContextEngine is an MCP server that implements a comprehensive Documentation Driven Development (DDD) system. It provides structured workflows, context management, and tools that enable AI assistants and humans to collaborate effectively through documentation-first development methodologies.
ContextEngine addresses the fundamental challenges of AI-human collaboration in software development:
- Context Management: Eliminates repetitive context provision by creating persistent documentation repositories
- Quality Assurance: Ensures code generation follows documented requirements and specifications
- Scalability: Handles 3x to 30x more information per person than traditional development methods
- Business Alignment: Maintains clear connection between technical implementation and business value
- Documentation-Driven Workflows: 9 standardized workflows for different development activities
- Context Engineering: Dynamic context composition and provision through knowledge graph
- Structured Documentation: Plan and task documents with hierarchical organization
- Local Documentation Setup: Automatic creation of organized folder structure and configuration files
- TypeScript: Full type safety and modern development experience
- Authentication: Built-in support for API keys and authentication
- Comprehensive Logging: Structured logging with proper MCP compatibility
- Node.js >= v18.0.0
- Cursor, Claude Code, VSCode, Windsurf or another MCP Client
``json`
"mcp": {
"servers": {
"context-engine": {
"type": "stdio",
"command": "npx",
"args": ["-y", "context-engine", "--api-key", "YOUR_API_KEY"]
}
}
}
ContextEngine provides tools for DDD workflow execution:
- Initializes the ContextEngine via API call to establish system awareness
- Creates local documentation structure with organized folders for DDD workflows
- Sets up configuration files with default settings and workflow definitions
- Provides comprehensive feedback about both remote and local setup status
The tool creates a .context-engine directory structure:``
.context-engine/
āāā implementation/ # For completed documentation and implementations
āāā requirements/ # For requirements and specifications
āāā config/ # For configuration files
āāā settings.json # ContextEngine settings
āāā workflows.json # Workflow configurations
Response Format: Returns a combined status showing both API response and local setup results with clear emoji indicators:
- š Success: Documentation structure setup completed
- ā ļø Warning: Setup completed with issues
- ā Error: Setup failed (but API call succeeded)
Your MCP server accepts the following CLI flags:
- --transport ā Transport to use (stdio by default)--port
- ā Port to listen on when using http transport (default 3000)--api-key
- ā API key for authentication (if needed)--server-url
- ā Custom server URL (defaults to https://contextengine.in)
1. Start ContextEngine: Use the start_context_engine` tool to initialize the DDD system and set up local documentation structure and local documentation setup results
2. Select Workflow: Choose from 9 available workflows based on your development objective
3. Execute Workflow: Follow the structured workflow phases to complete your development task
4. Integrate with AI assistants: Connect to Cursor, VS Code, Claude Code, etc.
MIT