
Context Manager MCP Server
A server implementation of the Model Context Protocol (MCP) for managing development workflow with features like project management, task tracking, and QA review support.
README
Context Manager MCP Server
A Model Context Protocol (MCP) server implementation for managing development context and workflow.
Features
- Socket-based transport with reliable message framing
- Full JSON-RPC 2.0 protocol support
- Session management with capability negotiation
- Extensible tool registry system
- Project, workpackage, and task management
- Checkpoint and restore functionality
- QA review workflow support
Initial Setup
# Install dependencies
npm install
# First-time build
npm run build
Usage
Starting the Server
# Development mode (no build required, uses tsx for on-the-fly compilation)
npm run dev
# Production mode (requires build)
npm start
# Start with debug logging
DEBUG=1 npm run dev
# Start on specific port
MCP_PORT=44558 npm run dev
Development Mode
# Run with hot reloading (preferred during development)
npm run dev
# Watch mode for TypeScript compilation (if you prefer running the compiled version)
npm run watch
# In a separate terminal when using watch mode
npm start
Clean Start
If you encounter any issues, you can try a clean build:
# Remove build artifacts
rm -rf dist/
# Reinstall dependencies
npm ci
# Rebuild the project
npm run build
# Start in development mode
npm run dev
Architecture
Core Components
-
Message Framing
- Content-Length based protocol
- Reliable message boundary handling
- Buffer management
-
Transport Layer
- TCP socket-based communication
- Connection management
- Event-driven architecture
-
Session Management
- Client session tracking
- Capability negotiation
- State persistence
-
Tool Registry
- Dynamic tool registration
- Input validation
- Result formatting
Tools
-
Project Management
- Create/Get projects
- Project checkpoints
- State restoration
-
Work Package Management
- Create/Get work packages
- Progress tracking
- Status updates
-
Task Management
- Create/Update tasks
- File change tracking
- Task checkpointing
-
QA Tools
- Review workflow
- Fix requests
- Work package acceptance
Configuration
Environment variables:
DEBUG
: Enable debug logging (0/1)MCP_PORT
: Server port (default: 44557)
Protocol
The server implements the Model Context Protocol with JSON-RPC 2.0:
interface MCPMessage {
jsonrpc: "2.0";
id: number;
method?: string; // for requests
params?: any; // for requests
result?: any; // for responses
error?: { // for error responses
code: number;
message: string;
data?: any;
};
}
Message Flow
- Client connects via TCP
- Client sends initialize request
- Server responds with capabilities
- Normal message exchange begins
- Client can shutdown/exit
Development
See Initial Setup and Development Mode sections above.
Contributing
- Fork the repository
- Create your feature branch
- Commit your changes
- Push to the branch
- Create a Pull Request
License
ISC License
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.

VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.

E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.