Manages a project memory bank using Markdown files, providing tools to initialize, read, and append to structured context files that maintain project knowledge across sessions.
Serves as the runtime environment for the memory bank system, allowing file operations to create, check, read, and update the contextual knowledge base.
This project implements the core functionality of the Roo Code Memory Bank system as a Model Context Protocol (MCP) server. It allows AI assistants to maintain project context across sessions by interacting with a file-based memory bank using structured MCP tools.
This MCP server provides the following tools:
initialize_memory_bank: Creates the memory-bank/ directory and standard .md files (productContext.md, activeContext.md, progress.md, decisionLog.md, systemPatterns.md) with initial templates.{ "project_brief_content": string }{ "status": "success" | "error", "messages"?: string[], "message"?: string }check_memory_bank_status: Checks if the memory-bank/ directory exists and lists the .md files within it.{}{ "exists": boolean, "files": string[] }read_memory_bank_file: Reads the full content of a specified memory bank file.{ "file_name": string }{ "content": string } or error object.append_memory_bank_entry: Appends a new, timestamped entry to a specified file, optionally under a specific markdown header. Creates the file if it doesn't exist.{ "file_name": string, "entry": string, "section_header"?: string }{ "status": "success" | "error", "message": string }dist/ directory.To make this server available to your AI assistant (like Cline), you need to add its configuration to your MCP settings file (e.g., cline_mcp_settings.json).
Find the mcpServers object in your settings file and add the following entry:
Important: Replace /path/to/your/cloned/repo/ with the correct absolute path to where you cloned the repository on your machine. Ensure the path separator is correct for your operating system (e.g., use backslashes \ on Windows).
You don't typically need to run the server manually. The MCP client (like Cline) will automatically start the server using the command and args specified in the configuration file when one of its tools is called for the first time.
If you want to test it manually, you can run npm start from the project directory.
The AI assistant interacts with the server using the defined tools. The typical workflow involves:
check_memory_bank_status).initialize_memory_bank).read_memory_bank_file) to gain context.append_memory_bank_entry) as decisions are made or progress occurs.The memory-bank/ directory will be created in the same directory where the server process is started (which should be the root of this project directory when launched via the MCP client configuration).
Set these instructions inside Roo
You must use MCPs where needed
I have a specific MCP flow:
Use context7 to find any relevant documentation pieces you will need for this process, ensure to feed any relevant knoweldege to any relevant subtasks - use context7 at all times to do research on important documentation if you're unsure of something Use google maps mcp in order to search for + - this will allow us to find the basic businesses we need to accomplish our task Use brave search mcp to find URLs to scrape Use fetch mcp with fetch_txt and fetch_markdown to find text and images on pages in order to convert into JSON files and create something in-depth Use openrouter search to find general sentiment of topics, reviews, etc.
Utilize the roo-code-memory-bank-mcp server to maintain project context:
check_memory_bank_status.exists: true), use read_memory_bank_file for relevant files (e.g., productContext.md, activeContext.md) to load the current project context.append_memory_bank_entry to record the information in the appropriate file (decisionLog.md, progress.md, etc.), ensuring context persistence.initialize_memory_bank if appropriate for the project.You must be authenticated.
local-only server
The server can only run on the client's local machine because it depends on local resources.
Enables AI assistants to maintain persistent project context across sessions by storing and retrieving structured information in markdown files organized in a memory bank directory.