The Memory Bank MCP server is a structured documentation system for project knowledge management with the following capabilities:
Initialize Memory Bank: Create a new documentation structure with templates, project goals, and optional Gemini API key
AI-Generated Documentation: Automatically generate project documentation using the Gemini API
Structured Knowledge System: Maintain six core document types in a hierarchical structure
Update Documents: Modify or regenerate specific documents manually or with AI assistance
Query Memory Bank: Search across all documents with context-aware relevance ranking
Export Documentation: Export in JSON or folder format to a specified location
MCP Integration: Seamlessly integrate with AI assistants via the Model Context Protocol
Generates and maintains interconnected Markdown documents that capture different aspects of project knowledge in a structured format
Memory Bank MCP
Note: This is not a traditional Node.js application. Memory Bank MCP is an MCP server—a component in the Model Context Protocol ecosystem. It exposes project knowledge to LLM-powered agents and tools using a standardized protocol, enabling seamless integration with AI clients (e.g., Claude Desktop, IDEs, or custom LLM agents).
What is Model Context Protocol (MCP)?
MCP is an open protocol that standardizes how applications provide context to LLMs. Think of MCP like a USB-C port for AI: it provides a universal way to connect AI models to data sources and tools, both locally and remotely. MCP enables:
- Plug-and-play integrations between LLMs, data, and tools
- Switching between LLM providers with minimal friction
- Secure, modular architecture for building AI workflows
Learn more: MCP Introduction
About Memory Bank MCP
Memory Bank MCP is an MCP server that helps teams create, manage, and access structured project documentation. It generates and maintains interconnected Markdown documents capturing all aspects of project knowledge, from high-level goals to technical details and daily progress. It is designed to be accessed by MCP-compatible clients and LLM agents.
Features
- AI-Generated Documentation: Uses Gemini API to generate and update project documentation
- Structured Knowledge System: Maintains six core document types in a hierarchical structure
- MCP Server: Implements the Model Context Protocol for integration with LLM agents and tools
- Customizable Storage: Choose where your Memory Bank directory is created
- Document Templates: Pre-defined templates for project brief, product context, system patterns, etc.
- AI-Assisted Updates: Update documents manually or regenerate them with AI
- Advanced Querying: Search across all documents with context-aware relevance ranking
Installation
Usage
Note: Memory Bank MCP is intended to be run as an MCP server, not as a standalone app. You typically launch it as part of an MCP workflow, and connect to it from an MCP-compatible client (such as Claude Desktop or your own LLM agent).
Development Mode
Production Mode
MCP Integration
To connect Memory Bank MCP to your MCP client, add the following to your mcp.json
configuration:
Replace /path/to/memory-bank-mcp/dist/index.js
with the absolute path to your built file, and add your Gemini API key if needed.
MCP Tools Exposed by Memory Bank
Memory Bank MCP provides the following tools via the Model Context Protocol:
initialize_memory_bank
Creates a new Memory Bank structure with all document templates.
Parameters:
goal
(string): Project goal description (min 10 characters)geminiApiKey
(string, optional): Gemini API key for document generationlocation
(string, optional): Absolute path where memory-bank folder will be created
Example:
update_document
Updates a specific document in the Memory Bank.
Parameters:
documentType
(enum): One of:projectbrief
,productContext
,systemPatterns
,techContext
,activeContext
,progress
content
(string, optional): New content for the documentregenerate
(boolean, default: false): Whether to regenerate the document using AI
Example:
query_memory_bank
Searches across all documents with context-aware relevance ranking.
Parameters:
query
(string): Search query (min 5 characters)
Example:
export_memory_bank
Exports all Memory Bank documents.
Parameters:
format
(enum, default: "folder"): Export format, either "json" or "folder"outputPath
(string, optional): Custom output path for the export
Example:
Document Types
Memory Bank organizes project knowledge into six core document types:
- Project Brief (
projectbrief.md
): Core document defining project objectives, scope, and vision - Product Context (
productContext.md
): Documents product functionality from a user perspective - System Patterns (
systemPatterns.md
): Establishes system architecture and component relationships - Tech Context (
techContext.md
): Specifies technology stack and implementation details - Active Context (
activeContext.md
): Tracks current tasks, open issues, and development focus - Progress (
progress.md
): Documents completed work, milestones, and project history
License
MIT
An MCP server that helps teams create, manage, and access structured project documentation through six core document types, leveraging AI to generate comprehensive project knowledge management.
Related MCP Servers
- -securityFlicense-qualityAn MCP server that provides AI tools with access to Rust documentation from docs.rs, enabling search for crates, documentation, type information, feature flags, version information, and source code.Last updated -23
- AsecurityAlicenseAqualityA Model Context Protocol server that enables AI assistants to interact with Linear project management systems, allowing users to retrieve, create, and update issues, projects, and teams through natural language.Last updated -4281099MIT License
- AsecurityFlicenseAqualityAn MCP server that supercharges AI assistants with powerful tools for software development, enabling research, planning, code generation, and project scaffolding through natural language interaction.Last updated -1151669
- -securityAlicense-qualityAn MCP server that automatically manages and organizes project documentation using the document reference pattern, keeping CLAUDE.md files clean and under 500 lines while maintaining full context for AI assistants.Last updated -MIT License