ContextEngine MCP Server
The ContextEngine MCP Server is a Model Context Protocol server that enables Documentation Driven Development (DDD) through structured AI-human collaboration workflows and intelligent context management.
Core Capabilities:
Initialize & Setup: Use
start_context_engineto automatically create local documentation structure (implemented/,requirements/,config/directories) and configure settingsExecute Workflows: Access 9 standardized documentation-driven workflows for development, supporting, and system activities
Manage Context: Leverage context engineering, knowledge graphs, and persistent documentation repositories to eliminate repetitive context provision
Quality Assurance: Align code generation with documented requirements and specifications through structured documentation hierarchies
Health Monitoring: Check API connectivity and system health with dedicated tools (
check-health,greet)
Integration Features:
Compatible with MCP clients like Cursor, Claude Code, VS Code, and Windsurf
Supports API key authentication and comprehensive structured logging
Enables dynamic context composition and hierarchical documentation organization
The server transforms development workflows by making documentation the foundation for AI-assisted coding, ensuring consistency and reducing context overhead.
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type
@followed by the MCP server name and your instructions, e.g., "@ContextEngine MCP Server show me the latest React hooks documentation"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
ContextEngine MCP Server
A 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.
π What is ContextEngine?
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.
Core Philosophy
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
Related MCP server: Context7 MCP
Features
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
π οΈ Installation
Requirements
Node.js >= v18.0.0
Cursor, Claude Code, VSCode, Windsurf or another MCP Client
Connecting to MCP Clients
"mcp": {
"servers": {
"context-engine": {
"type": "stdio",
"command": "npx",
"args": ["-y", "context-engine", "--api-key", "YOUR_API_KEY"]
}
}
}π¨ Available Tools
ContextEngine provides tools for DDD workflow execution:
1. start_context_engine
Starts the ContextEngine system and automatically sets up the local documentation structure. This tool:
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/
βββ implementation/ # For completed documentation and implementations
βββ requirements/ # For requirements and specifications
βββ config/ # For configuration files
βββ settings.json # ContextEngine settings
βββ workflows.json # Workflow configurationsResponse Format: Returns a combined status showing both API response and local setup results with clear emoji indicators:
π Success: Documentation structure setup completed
β οΈ Warning: Setup completed with issues
β Error: Setup failed (but API call succeeded)
CLI Arguments
Your MCP server accepts the following CLI flags:
--transport <stdio|http>β Transport to use (stdioby default)--port <number>β Port to listen on when usinghttptransport (default3000)--api-key <key>β API key for authentication (if needed)--server-url <url>β Custom server URL (defaults to https://contextengine.in)
π Usage
Start ContextEngine: Use the
start_context_enginetool to initialize the DDD system and set up local documentation structure and local documentation setup resultsSelect Workflow: Choose from 9 available workflows based on your development objective
Execute Workflow: Follow the structured workflow phases to complete your development task
Integrate with AI assistants: Connect to Cursor, VS Code, Claude Code, etc.
π License
MIT
Available Tools
1 toolstart_context_engineStart Context EngineC
Starts the context engine and returns a confirmation message.
Inputs: projectRoot (required).
Tool Schema Changelog
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
Loading tool schema changelogβ¦
TDQS
Scored across 1 tool
With only a single tool, there is no possibility of confusion or overlapping purposes. The tool's purpose is clear and unique within the set.
The single tool name follows a clear verb_noun pattern ('start_context_engine'). With only one tool, the naming is internally consistent and predictable.
A single trivial start tool is an extreme mismatch for a server purporting to be a 'ContextEngine'. The server appears far too thin to be useful for any meaningful workflow.
The server offers only a start operation with no corresponding stop, status, configuration, or query capabilities. This is severely incomplete for any engine lifecycle or context management purpose.
Maintenance
Related MCP Connectors
@latest documentation and code examples to 9000+ libraries for LLMs and AI code editors in a singlβ¦
Provide your AI coding tools with token-efficient access to up-to-date technical documentation forβ¦
Find open-source libraries and fetch contextual code snippets by version to accelerate developmentβ¦
Docsy gives AI assistants current, version-specific documentation for libraries, frameworks and SDKs. Resolve library IDs and versions, then search and fetch focused official documentation with original source links using five read-only MCP tools. Hosted Streamable HTTP with OAuth 2.1 sign-in.
Related MCP Servers
- AlicenseAqualityDmaintenanceProvides up-to-date, version-specific documentation and code examples for libraries and frameworks directly into AI prompts, eliminating outdated code generation and hallucinated APIs.2MIT
- AlicenseAqualityDmaintenanceProvides LLMs with up-to-date, version-specific documentation and code examples directly from library sources, eliminating outdated training data and hallucinated APIs by fetching current documentation at prompt time.2MIT
- AlicenseNot gradedqualityDmaintenanceProvides up-to-date, version-specific documentation and code examples for software libraries directly to LLMs, enabling resolution of library identifiers and retrieval of relevant documentation with code snippets.MIT

xenodocs-mcp-serverofficial
AlicenseAqualityDmaintenanceFetches up-to-date, version-specific documentation and code examples for any library, preventing outdated or hallucinated API usage in LLM responses.2MIT