广告合作
MCP.so
登录

Memory Bank MCP Server

@alioshr

代码仓库主页

基本信息

分类

记忆与知识

许可证

MIT

传输方式

stdio

作者

alioshr

关于 Memory Bank MCP Server

A Model Context Protocol (MCP) server implementation for remote memory bank management, inspired by Cline Memory Bank.

#cursor#cline#claude#windsurf#memory-bank#model-context-protocol#mcp-server#antrophic#cline-memory-bank

Memory Bank MCP Server 配置

使用下面的配置,将此服务器添加到你的 MCP 客户端。

{
  "mcpServers": {
    "memory-bank-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "@smithery/cli",
        "install",
        "@alioshr/memory-bank-mcp",
        "--client",
        "claude"
      ]
    }
  }
}

Memory Bank MCP Server 工具

工具列表暂未提供

当前收录暂时没有可展示的工具列表，不代表服务没有工具。请查阅项目文档了解支持的能力。

点击上方按钮,在临时沙箱中运行此服务器并实时获取工具列表。

概览

What is Memory Bank MCP Server?

Memory Bank MCP Server is a Model Context Protocol (MCP) server for remote memory bank management, inspired by Cline Memory Bank. It transforms file-based memory banks into a centralized service, offering remote access, multi‑project management, consistent file structure, and project isolation.

How to use Memory Bank MCP Server?

Configure the server in your MCP client’s settings (Claude Desktop, Claude Code, Cursor, Cline, or Roo Code) by setting the environment variable MEMORY_BANK_ROOT to the directory where project memory banks are stored. Use npx -y @allpepper/memory-bank-mcp as the command. After configuration, your AI assistant can invoke tools like memory_bank_read, memory_bank_write, memory_bank_update, list_projects, and list_project_files.

Key features of Memory Bank MCP Server

  • Multi‑project support with project‑specific directories and file structure enforcement
  • Remote accessibility via full MCP protocol with type‑safe operations
  • Core operations: read, write, update, list projects, and list project files
  • Project isolation with path traversal prevention
  • Security through proper error handling and isolated directories

Use cases of Memory Bank MCP Server

  • Centralizing memory bank files for multiple projects in one service
  • Providing remote AI assistants with consistent access to project documentation
  • Maintaining structured and validated memory bank files across teams
  • Enabling safe read‑only operations for verification and auditing

常见问题

1

How do I install Memory Bank MCP Server?

You can install it automatically via Smithery (`npx -y @smithery/cli install @alioshr/memory-bank-mcp --client claude`) or manually by adding the npx command to your MCP client configuration.

2

What configuration is required?

Set the `MEMORY_BANK_ROOT` environment variable to the absolute path of the directory where project memory banks are stored. Optionally, you can define `autoApprove` operations to skip user prompts for trusted actions.

3

Which MCP clients are supported?

The server works with Claude Desktop, Claude Code, Cursor, Cline, and Roo Code. Each client requires a slightly different configuration file path and format, as described in the README.

4

What operations can I use?

The server provides five tools: `memory_bank_read`, `memory_bank_write`, `memory_bank_update`, `list_projects`, and `list_project_files`. These cover reading, creating, and updating memory bank files, as well as enumerating projects and project files.

评论

记忆与知识 分类下的更多 MCP 服务器

The Cloud

Teka

The Cloud is the AI-native workspace that gives every AI — Claude, ChatGPT, Gemini, and other Frontier & Free or Local models — shared memory and real agents. Not cloud computing: thecloud.so is one workspace where your

Leviathan Systems Public Content MCP

Leviathan Systems

Search published GPU deployment, rack integration and structured cabling resources; read canonical documents and Leviathan Systems company service scope. Anonymous, read-only Streamable HTTP MCP. No credentials required.

ctxfile

ctxfile

Local-first MCP server that snapshots your project's working state into one context object. Open-core, privacy-first.

2

Context7 MCP - Up-to-date Docs For Any Cursor Prompt

upstash

Context7 Platform -- Up-to-date code documentation for LLMs and AI code editors

58.7K

Agimem

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

广告合作