MCP.so
登录

IDE Memory MCP Server

@prasanna00019

基本信息

分类

记忆与知识

传输方式

stdio

作者

prasanna00019

提交者

Prasanna H

关于 IDE Memory MCP Server

IDE Memory MCP gives AI coding agents a persistent memory layer that works across any IDE supporting the Model Context Protocol. Write project context once — the AI remembers it everywhere.

IDE Memory 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": {
    "IDE-Memory-MCP": {
      "command": "uv",
      "args": [
        "pip",
        "install",
        "ide-memory-mcp"
      ]
    }
  }
}

IDE Memory 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。

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 IDE Memory MCP?

Cross‑IDE persistent memory for AI coding agents. It remembers project context—architecture, decisions, progress—across any IDE that supports the Model Context Protocol (Cursor, VS Code, Windsurf, Claude Desktop). Built for developers who use AI assistants and want to stop repeating themselves.

How to use IDE Memory MCP?

Install the package with pip install ide-memory-mcp (or uv pip install ide-memory-mcp). Run ide-memory-mcp setup to auto‑configure your IDEs, then restart your IDE. Manual configuration is also available via IDE‑specific JSON files.

Key features of IDE Memory MCP

  • Cross‑IDE memory persistence across multiple MCP‑compatible IDEs
  • Context‑optimized reads that return a compact summary table
  • Smart warnings for stale, oversized, or old memory sections
  • Built‑in agent prompts for session start, bootstrap, and updates
  • Section‑based storage: overview, decisions, active_context, progress
  • Append mode for incremental updates without overwriting

Use cases of IDE Memory MCP

  • Start a fresh AI conversation and instantly recall project context
  • Onboard an AI agent to an existing project by bootstrapping memory
  • Track ongoing work and decisions across multiple IDEs
  • Automatically prune stale memory to keep the context window efficient

常见问题

1

Where is memory data stored?

All memory is stored as local markdown files in `~/.ide-memory/projects/`. No database or cloud service is required; data never leaves your machine.

2

How do I install IDE Memory MCP?

Install with `pip install ide-memory-mcp` or `uv pip install ide-memory-mcp`. The server requires Python 3.11+.

3

How does IDE Memory MCP handle stale memory?

It automatically detects sections not updated for >7 days (stale), sections exceeding 10k characters (large), and sections older than 30 days (pr

评论

记忆与知识 分类下的更多 MCP 服务器