Memory Bank MCP Server logo

Memory Bank MCP Server

by t3ta

A Memory Bank implementation for managing project documentation and context across sessions using the Model Context Protocol (MCP). This server helps AI agents maintain consistent project knowledge through global and branch-specific memory banks.

View on GitHub

Last updated: N/A

What is Memory Bank MCP Server?

The Memory Bank MCP Server is a server that manages project documentation and context for AI agents using the Model Context Protocol (MCP). It stores project knowledge in global and branch-specific memory banks in a structured JSON format, allowing AI agents to maintain consistent project understanding across sessions.

How to use Memory Bank MCP Server?

To use the server, clone the repository, install dependencies using Yarn, and then run the server using the command yarn workspace @memory-bank/mcp start --docs /path/to/your/docs, replacing /path/to/your/docs with the path to your project's documentation directory.

Key features of Memory Bank MCP Server

  • Manages project documentation and context

  • Uses Model Context Protocol (MCP)

  • Stores memory banks in structured JSON format

  • Supports global and branch-specific memory banks

Use cases of Memory Bank MCP Server

  • Maintaining consistent project knowledge for AI agents

  • Providing context for AI agents across sessions

  • Managing documentation for large projects

  • Enabling AI agents to understand project history and context

FAQ from Memory Bank MCP Server

What is MCP?

MCP stands for Model Context Protocol, a protocol for managing context for AI models.

What is a memory bank?

A memory bank is a structured storage of project knowledge and context.

How do I install the server?

Clone the repository and run yarn install.

How do I start the server?

Run yarn workspace @memory-bank/mcp start --docs /path/to/your/docs.

Where can I find more details?

See the packages/mcp/README.md file for more details.