Memory Bank MCP Server

@TerLand0berver

Repository

Basic information

About Memory Bank MCP Server

No overview available yet

#memory-bank #mcp-server #data-management

Memory Bank MCP Server config

Add this server to your MCP-compatible client using the configuration below.

{
  "mcpServers": {
    "memory-bank-mcp-server-terland0berver": {
      "command": "npx",
      "args": [
        "@telagod/memory-bank-mcp-server"
      ]
    }
  }
}

Memory Bank MCP Server tools

Tool list not available yet

This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.

Fetch the live tool list by running this server in a temporary sandbox using the button above.

Overview

What is Memory Bank MCP Server?

A Model Context Protocol (MCP) server that manages project-specific "memory bank" data using an SQLite database. It stores and retrieves contextual project information such as product background, decision logs, and progress updates, and is intended for AI-assisted development workflows using MCP-enabled applications like RooCode.

How to use Memory Bank MCP Server?

The server is run via npx @telagod/memory-bank-mcp-server and requires Node.js version 18.0.0 or higher. It is typically started automatically by an MCP host application (e.g., RooCode) configured through mcp_settings.json using the provided npx command and arguments.

Key features of Memory Bank MCP Server

Project-based: separate memory bank per project path.
SQLite storage in memory-bank/memory.db within the project directory.
Modular MCP service encapsulating memory bank logic.
Provides MCP tools: initialize_memory_bank, get_memory_bank_status, read_memory_bank_section, update_memory_bank_entry.

Use cases of Memory Bank MCP Server

Initializing a memory bank when starting work on a new project.
Recording technical decisions and their rationale for future reference.
Tracking development progress and milestone status.
Defining current focus areas and issues needing attention.
Documenting reusable system patterns and design principles.

Frequently asked questions

What Node.js version is required?

Node.js version 18.0.0 or higher is required to run the server.

Where is the memory bank data stored?

Data is stored in an SQLite database file at `memory-bank/memory.db` inside the specified project directory.

How do I integrate this server with RooCode?

Add a configuration entry to RooCode's `mcp_settings.json` file using the command `npx` with arguments `-y @telagod/memory-bank-mcp-server` and the desired allowed tools.

What sections are available in the memory bank?

The server manages five sections: `product_context`, `decisions`, `progress`, `focus`, and `system_patterns`, each represented by a table in the SQLite database.

How is the server started?

It is typically started automatically by an MCP host application (like RooCode) via the `npx` command, but can also be launched manually using `npx @telagod/memory-bank-mcp-server`.

Comments

More Memory & Knowledge MCP servers

UmmahAPI

Yousuf Kazmi

Islamic source data for assistants: Quran, hadith, tafsir, duas, prayer times and qibla. Answers come from real sources with citations instead of recalled text, so verses and hadith are not hallucinated. 36,000+ hadiths

Sooveryn

PANDAPROG

Sooveryn gives Claude Code a team of AI personas that remembers your project. Soov, the partner and team lead, keeps your decisions and how you work in a lasting memory, and finds them again by words and by meaning, from

PLUR

plur-ai

AI agents start every session with amnesia — you re-explain the project, repeat your preferences, and correct the same mistakes over and over. PLUR gives them a memory that persists. Your agent's corrections, preference

226

Agimem

Persistent memory for AI agents. Hosted MCP server with capsule-scoped key/value storage, tags, TTL expiration, bulk ops, and RBAC.

OpenLore

aakarim

Serve your docs to AI agents over SSH and MCP. Agents use ls, cat, grep, find, and pipes against a virtual filesystem backed by your documentation. Identity-scoped access, governed writing with human approval, and portab