🧠 Memory MCP Server - Orchestrator

What is Memory MCP Server - Orchestrator?

Memory MCP Server - Orchestrator is a Model Context Protocol (MCP) server that gives AI agents persistent memory, task planning, and knowledge management. Built with TypeScript and SQLite, it requires a separate workflow.md file to operate as an intelligent system. It is designed for AI agents in MCP-compatible clients.

How to use Memory MCP Server - Orchestrator?

Install Node.js 18+, npm, and Git. Clone the repository, run npm install and npm run build, then verify with npm run test. Configure the server in your MCP client (e.g., VS Code Cline) with the node command pointing to build/index.js, and set the GEMINI_API_KEY and TAVILY_API_KEY environment variables. Critical: Load the workflow.md file into your AI agent’s system prompt to enable the six‑mode operational structure.

Key features of Memory MCP Server - Orchestrator

• Conversation history with full context storage
• Version‑controlled dynamic context storage
• Knowledge graph for entity relationship management
• Vector embeddings for semantic search
• AI‑powered planning with hierarchical tasks and dependencies
• Google Gemini integration for prompt refinement, summarization, and more
• Tavily web search integration
• Data validation, logging, backup, and restore

Use cases of Memory MCP Server - Orchestrator

• Giving AI agents persistent memory across sessions
• Structuring complex task planning and execution with a proven workflow
• Building and querying a knowledge graph of entities and relationships
• Enhancing AI capabilities with external search and AI summarization
• Enforcing safety protocols and user approval for state changes

FAQ from Memory MCP Server - Orchestrator

What is the AI Driver (workflow.md)?

It is a mandatory file that defines six operational modes (Prompt Refine, Think, Code Analysis, Innovate, Plan, Execute, Review), safety rules, and a workflow state machine. It must be loaded into the AI agent’s system prompt for the server to function as an intelligent system.

Does this server require external API keys?

Yes. It needs GEMINI_API_KEY for Google Gemini integration and TAVILY_API_KEY for Tavily web search. Both are configured as environment variables in the MCP client settings.

What transport does the server use?

The server communicates over stdio transport, as shown in the configuration example for MCP clients.

Where is data stored?

Data is stored locally in a SQLite database. The server provides backup and restore capabilities for that database.

What are the system requirements?

Node.js 18.x or higher, npm (latest), and Git. The server is built with TypeScript 5.3+.