Memory Bank MCP
@tuncer-byte
About Memory Bank MCP
Memory Bank is an MCP server that helps teams create, manage, and access structured project documentation. It generates and maintains a set of interconnected Markdown documents that capture different aspects of project knowledge, from high-level goals to technical details and day
Config
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"memoryBank": {
"command": "node",
"args": [
"/path/to/memory-bank-mcp/dist/index.js"
],
"env": {
"GEMINI_API_KEY": ""
}
}
}
}Tools
No tools detected
We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.
Overview
What is 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.
How to use Memory Bank MCP?
Install via git clone and npm install. Configure with a Gemini API key via a .env file or the mcp.json configuration. Run in development mode with npm run dev or in production mode after npm run build && npm run start. Add the server to your MCP client’s mcp.json to expose its tools for initialization, document updates, querying, and export.
Key features of Memory Bank MCP
- AI-generated documentation using the Gemini API
- Structured knowledge system with six core document types
- Implements the Model Context Protocol for LLM integration
- Customizable storage location for the Memory Bank directory
- Pre-defined templates for project brief, product context, and more
- Advanced querying with context-aware relevance ranking
Use cases of Memory Bank MCP
- Initialize a new project memory bank with all document templates
- Update project documentation manually or regenerate it with AI
- Search across all Memory Bank documents for relevant context
- Export Memory Bank documents in JSON or folder format
FAQ from Memory Bank MCP
Is Memory Bank MCP a standalone application?
No, it is an MCP server—it is meant to be connected to MCP-compatible clients such as Claude Desktop or custom LLM agents, not run as a standalone app.
What runtime and environment does Memory Bank MCP require?
Node.js is required. Dependencies are installed via npm install. A Gemini API key is needed for AI-powered document generation and updates.
Where does Memory Bank MCP store project data?
Data is stored in a user-specified directory. The location parameter during initialization determines where the memory-bank folder is created.
What API key is needed for AI features?
A Gemini API key is required. It can be provided through a .env file or the GEMINI_API_KEY environment variable in the MCP client configuration.
How do I expose Memory Bank MCP tools to my client?
Add the server definition to your MCP client’s mcp.json file, specifying the command (node), the path to the built index.js, and optionally the Gemini API key. The server then exposes tools like initialize_memory_bank, update_document, query_memory_bank, and export_memory_bank.
Frequently asked questions
Is Memory Bank MCP a standalone application?
No, it is an MCP server—it is meant to be connected to MCP-compatible clients such as Claude Desktop or custom LLM agents, not run as a standalone app.
What runtime and environment does Memory Bank MCP require?
Node.js is required. Dependencies are installed via `npm install`. A Gemini API key is needed for AI-powered document generation and updates.
Where does Memory Bank MCP store project data?
Data is stored in a user-specified directory. The `location` parameter during initialization determines where the memory-bank folder is created.
What API key is needed for AI features?
A Gemini API key is required. It can be provided through a `.env` file or the `GEMINI_API_KEY` environment variable in the MCP client configuration.
How do I expose Memory Bank MCP tools to my client?
Add the server definition to your MCP client’s `mcp.json` file, specifying the command (`node`), the path to the built `index.js`, and optionally the Gemini API key. The server then exposes tools like `initialize_memory_bank`, `update_document`, `query_memory_bank`, and `export_memory_bank`.
Basic information
More Memory & Knowledge MCP servers
Obsidian MCP Server
StevenStavrakisA simple MCP server for Obsidian
MemoryMesh
CheMiguel23A knowledge graph server that uses the Model Context Protocol (MCP) to provide structured memory persistence for AI models.
Obsidian MCP Server
cyanheadsRead, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.
RAG Documentation MCP Server
hannesrudolphAn MCP server implementation that provides tools for retrieving and processing documentation through vector search, enabling AI assistants to augment their responses with relevant documentation context.
Notion MCP Server
suekouA Model Context Protocol server for connecting Notion to MCP-compatible clients
Comments