Roo Code Memory Bank MCP Server
@IncomeStreamSurfer
关于 Roo Code Memory Bank MCP Server
暂无概览
基本信息
配置
工具
未检测到工具
工具是从 README 中自动提取的。维护者可以在 ## Tools 标题下列出工具,即可填充这部分内容。
概览
What is Roo Code Memory Bank MCP Server?
This server 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.
How to use Roo Code Memory Bank MCP Server?
Clone the repository, run npm install and npm run build, then configure the server in your MCP client settings (e.g., cline_mcp_settings.json) by specifying the command as node with the path to dist/index.js. The AI assistant uses the tools to check the memory bank status, initialize if needed, read files for context, and append entries for decisions and progress. The memory bank is stored in a memory-bank/ directory in the project root.
Key features of Roo Code Memory Bank MCP Server
- Provides four MCP tools: initialize, check, read, and append.
- Creates standard memory bank files with templates.
- Supports timestamped entries under optional markdown headers.
- Runs via stdio transport, launched automatically by MCP client.
- File-based storage requires no external database.
Use cases of Roo Code Memory Bank MCP Server
- AI assistant resumes a long project session with full context.
- Record decisions and progress during development work.
- Maintain structured documentation like product context and system patterns.
- Collaborate across multiple sessions without losing project state.
FAQ from Roo Code Memory Bank MCP Server
What dependencies or runtime are required?
Node.js v18 or later and npm are required. An MCP client environment (like Cline) is needed to launch the server.
How do I configure the server for Cline?
Add an entry to cline_mcp_settings.json under mcpServers with the command node and args pointing to the absolute path of dist/index.js. The transportType must be "stdio".
Where is the memory bank data stored?
The memory bank is created as a memory-bank/ directory in the same directory where the server process is started (the project root when launched via the MCP client configuration).
What known limits are there?
The README does not state explicit limits. The server is file-based and runs locally; no network transport or authentication is mentioned.
What tools are provided and what do they do?
initialize_memory_bank creates the directory and template files; check_memory_bank_status checks existence and lists files; read_memory_bank_file returns full file content; append_memory_bank_entry appends a timestamped entry, optionally under a section header.
记忆与知识 分类下的更多 MCP 服务器
Notion MCP Integration
danhilseA simple MCP integration that allows Claude to read and manage a personal Notion todo list

Dash Api Docs Mcp Server
KapeliMCP server for Dash, the macOS API documentation browser
Semantic Scholar MCP Server
YUZongminA FastMCP server implementation for the Semantic Scholar API, providing comprehensive access to academic paper data, author information, and citation networks.
Basic Memory
basicmachines-coAI conversations that actually remember. Never re-explain your project to your AI again. Join our Discord: https://discord.gg/tyvKNccgqN
Ultimate Google Docs & Drive MCP Server
a-bonusThe Ultimate Google Docs, Sheets, Drive, Gmail, & Google Calendar MCP Server. This MCP (primarily for use in Claude Desktop) gains full access to your google suite and lets claude do its thing.
评论