IDE Memory MCP

by prasanna00019

125 downloads
Not rated
GitHub

About

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.

Details

Author
prasanna00019
Downloads
125
Categories
Knowledge Base, Database, File Management, Other, Developer Tools, AI, Productivity

- 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

Setting up with Highlight

This MCP is not yet compatible with Highlight’s one-click setup. However, you can still use it with Highlight by following these steps:

  1. Download and install Highlight from highlightai.com/download
  2. Navigate to the plugins tab and select "Add Custom Plugin"
  3. Configure the plugin with the settings below
    Plugin Name IDE Memory MCP
    Command (node, npx, python, etc.)

    Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.

  4. Enable "Start Automatically" if you want the plugin to start when Highlight launches

From the repository

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.

Claude Desktop / Cursor

Paste into your MCP client config file to install this server.

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

McpServers

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

IDE Memory MCP

<p align="center"> IDE Memory MCP </p> > Cross-IDE persistent memory for AI coding agents — your AI remembers every project, across every IDE. Python 3.11+ License: MIT MCP ---

The Problem

Every time you open a project in a new IDE or start a fresh AI conversation, your AI assistant forgets everything: - What the project does - Architecture decisions you've made - What you're currently working on - Your progress and milestones You end up repeating yourself. Every. Single. Time.

The Solution

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. `` Cursor ←──→ IDE Memory MCP ←──→ VS Code ↑ ↓ ↑ └── same project memory ────────┘ ` ---

Key Features

- Cross-IDE Memory — Project context persists across Cursor, VS Code, Windsurf, Claude Desktop, and any MCP-compatible IDE - Context-Optimized — Default reads return a compact summary table, not a context-window-destroying content dump. The AI loads only what it needs. - Smart Warnings — Automatically detects stale sections (>7 days), oversized content (>10k chars), and suggests pruning when memory gets old (>30 days) - Agent Prompts — Built-in MCP prompts guide the AI on how to start sessions, bootstrap memory for new projects, and update memory after changes - Smart Project Matching — Recognizes projects by path or git remote URL. Move folders, switch machines — your memory follows. - Section-Based Storage — Organized into
overview, decisions, active_context, progress + custom sections - Append Mode — Add incremental updates without rewriting entire sections - Version History — Previous content auto-saved before each overwrite (last 5 snapshots) - Zero Config — Works out of the box. No database, no cloud, just local markdown files. ---

Quick Start

1. Install

``bash
No reviews yet — be the first

Sign in to leave a review

Use Google, GitHub, or an email account so ratings stay tied to real people.

Email sign in

No reviews posted yet.