MCP Context Manager
@tejpalvirk
MCP Servers for persistent context across work sessions using knowledge graphs
Overview
What is MCP Context Manager?
MCP Context Manager is a collection of Model Context Protocol (MCP) servers that provide AI models with persistent context across work sessions throughout the project lifecycle. It stores context in domain‑specific knowledge graphs and offers a central manager for unified access to multiple domain servers.
How to use MCP Context Manager?
Install via npx github:tejpalvirk/contextmanager (recommended) or globally with npm install -g github:tejpalvirk/contextmanager and run mcp-server-contextmanager. Use tools such as setActiveDomain, startsession, endsession, buildcontext, loadcontext, and deletecontext to manage context. Configure domain selection with the --domains flag and data paths with environment variables MEMORY_FILE_PATH and SESSIONS_FILE_PATH.
Key features of MCP Context Manager
- Persistent context with buildcontext, loadcontext, and deletecontext tools
- Session management with startsession and endsession tools
- Cross‑domain support for relationships between different knowledge domains
- Knowledge graph storage for token efficiency and context window performance
- Unified interface with smart routing to domain‑specific servers
- Standardized status, priority, and sequencing across domains
Use cases of MCP Context Manager
- Manage software development context (projects, components, tasks) with status and priority tracking
- Handle project management knowledge (tasks, resources) with sequencing and progress tracking
- Support educational workflows (courses, assignments, exams) with learning sequences
- Organize qualitative research data (studies, participants, interviews) with analysis sequencing
- Structure quantitative research datasets (variables, analyses) with sequential process management
FAQ from MCP Context Manager
What problem does MCP Context Manager solve compared to plain context windows?
It uses knowledge graphs to free up the AI’s context window (performance) and minimize token cost (efficiency), providing persistent, organized context across sessions.
What are the runtime requirements?
Node.js v16 or higher and npm v7 or higher are required. No external databases or services are needed beyond the local file system.
Where does the knowledge graph data live?
Data is stored in two files per domain: a memory file (default <domain_directory>/memory.json) and a sessions file (default <domain_directory>/sessions.json). Paths can be customized with environment variables MEMORY_FILE_PATH and SESSIONS_FILE_PATH.
What transport protocol does MCP Context Manager use?
It uses the MCP Client SDK to communicate between the Context Manager and domain servers, and it exposes an MCP server interface for integration with clients like Claude Desktop.
How do I handle a “port already in use” error?
Use the --port argument to specify a different port (default is 3000), for example npx github:tejpalvirk/contextmanager --port 3001.