IDE Memory MCP

@prasanna00019

About IDE Memory MCP

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.

Config

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

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

Tools

No tools detected

We auto-extract tools from the README. The maintainer can list them under a ## Tools heading to populate this section.

Overview

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

FAQ from IDE Memory MCP

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.

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+.

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

Frequently asked questions

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.

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+.

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

Comments

Basic information

More Memory & Knowledge MCP servers

MemoryMesh

CheMiguel23

A knowledge graph server that uses the Model Context Protocol (MCP) to provide structured memory persistence for AI models.

348

Solomd

zhitongblog

A markdown editor — and the bridge to your LLM. Local-first, MIT, ~15 MB. Bundled MCP server lets Claude Code / Codex / Cursor drive your vault directly. 14 AI providers BYOK.

425

Anytype MCP Server

anyproto

An MCP server enabling AI assistants to interact with Anytype - your encrypted, local and collaborative wiki - to organize objects, lists, and more through natural language.

467

Context Portal MCP (ConPort)

GreatScottyMac

Context Portal (ConPort): A memory bank MCP server building a project-specific knowledge graph to supercharge AI assistants. Enables powerful Retrieval Augmented Generation (RAG) for context-aware development in your IDE.

763

Obsidian MCP Server

cyanheads

Read, write, search, and surgically edit Obsidian vault notes, tags, and frontmatter via MCP. STDIO or Streamable HTTP.

618