Happy slice of mcp pizzaMCP.pizza
Fire in da houseTop Tip:Paying $100+ per month for Perplexity, MidJourney, Runway, ChatGPT and other tools is crazy - get all your AI tools in one site starting at $15 per month with Galaxy AI Fire in da houseCheck it out free

memory-bank-mcp-server

MCP.Pizza Chef: t3ta

The Memory Bank MCP Server is a specialized MCP server that manages project documentation and context across sessions using structured JSON memory banks. It supports global and branch-specific memory storage, enabling AI agents like Claude to maintain consistent and up-to-date project knowledge. This server facilitates persistent context management for multi-session workflows, improving continuity and accuracy in AI-assisted projects.

Use This MCP server To

Store and retrieve project documentation across multiple sessions Maintain consistent AI agent knowledge with global memory banks Manage branch-specific context for versioned project workflows Enable AI agents to access structured project memory in JSON format Support multi-session context continuity for AI-assisted development Facilitate memory bank operations and MCP tool execution Integrate with AI agents like Claude for enhanced project understanding

README

Memory Bank MCP Server

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

This project is inspired by Cline Memory Bank from the nickbaumann98/cline_docs repository.

Packages

This repository is a monorepo managed with Yarn Workspaces. It contains the following packages:

  • packages/mcp: The core MCP server implementation. Contains the main logic for handling memory bank operations, MCP tool execution, and server startup.
  • packages/schemas: Defines the JSON schemas used for memory bank documents (e.g., memory_document_v2).
  • packages/vscode-extension: A VSCode extension providing integration with the Memory Bank MCP server (details TBD).

Getting Started

Prerequisites

  • Node.js (see .tool-versions for recommended version)
  • Yarn (v1.x)

Installation

Clone the repository and install dependencies from the root directory:

git clone https://github.com/t3ta/memory-bank-mcp-server.git
cd memory-bank-mcp-server
yarn install

Running the MCP Server

You can run the MCP server directly from the monorepo:

# From the monorepo root directory
yarn workspace @memory-bank/mcp start --docs /path/to/your/docs

Replace /path/to/your/docs with the actual path to your project's documentation directory (where global-memory-bank and branch-memory-bank will reside or be created).

See the packages/mcp/README.md for more details on running the server and its options.

Development

  • Build all packages: yarn build
  • Run tests for all packages: yarn test
  • Lint code: yarn lint

Refer to the README file within each package directory for package-specific development instructions.

License

This project is licensed under the MIT License. See the LICENSE file for details.

memory-bank-mcp-server FAQ

How does the Memory Bank MCP Server store project context?
It stores project documentation and context in structured JSON memory banks, supporting both global and branch-specific data.
Can this server handle multiple project branches?
Yes, it manages branch-specific memory banks to maintain context for different project versions.
Which AI agents can use this Memory Bank MCP Server?
It is designed to work with AI agents like Claude and can be adapted for others supporting MCP.
How does this server improve AI project workflows?
By maintaining persistent, structured memory across sessions, it ensures AI agents have consistent and accurate project knowledge.
Is the Memory Bank MCP Server customizable?
Yes, it is implemented as a monorepo with modular packages, allowing customization of memory schemas and server logic.
What formats does the server use for memory storage?
It uses JSON schemas to structure and validate memory bank documents.
How is the server deployed and managed?
The server is managed via Yarn Workspaces in a monorepo setup, facilitating modular development and deployment.