🧠 Smart Workspace Manager
About
# 🧠 Smart Workspace Manager > Supercharge your productivity by connecting your personal workspace to AI. Smart Workspace Manager is a secure, local-first [Model Context Protocol (MCP)](https://modelcontextprotocol.io/) server that exposes your files, notes, and projects to AI assistants like Claude Desktop, Cursor…
Details
- License
- MIT license
Explore
- 📚 Resource Discovery: Files, folders, and notes exposed as structured MCP Resources.
- 🔎 Smart Search: Search workspace contents by name, path, or keywords.
- 📝 Document Summarization: Quickly summarize meeting notes, articles, or project plans.
- 🗂️ File Creation and Organization: Create, rename, move, and (optionally) delete files.
- ⚙️ Configurable and Secure: Full control over file types, size limits, and writable actions.
- 🔌 MCP Compatible: Connects to any MCP-enabled client without custom integration.
- 🛡️ Local-First Privacy: Your data never leaves your machine.
---
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:
- Download and install Highlight from highlightai.com/download
- Navigate to the plugins tab and select "Add Custom Plugin"
-
Configure the plugin with the settings below
Plugin Name
🧠 Smart Workspace ManagerCommand (node, npx, python, etc.)Please refer to the README for specific instructions on how to obtain API keys or other required environment variables.
- Enable "Start Automatically" if you want the plugin to start when Highlight launches
From the repository
- macOS (Silicon / ARM64)
- Python 3.10+
- Node.js (optional, for testing tools like MCP Inspector)
- MCP-compatible client (e.g., Claude Desktop)
python3 -m venv venv
source venv/bin/activate
pip install -r requirements.txt
python server.py
```
Or launch automatically via your MCP client (e.g., Claude Desktop config).
---
Claude Desktop / Cursor
Paste into your MCP client config file to install this server.
{
"mcpServers": {
"\ud83e\udde0 smart workspace manager": {
"Smart-Workspace-Manager-MCP-Server": {
"command": "python3",
"args": [
"-m",
"venv",
"venv"
]
}
}
}
}McpServers
{
"Smart-Workspace-Manager-MCP-Server": {
"command": "python3",
"args": [
"-m",
"venv",
"venv"
]
}
}> Supercharge your productivity by connecting your personal workspace to AI.
Smart Workspace Manager is a secure, local-first Model Context Protocol (MCP) server that exposes your files, notes, and projects to AI assistants like Claude Desktop, Cursor IDE, and custom LLM workflows.
Built for macOS (Silicon) developers, it bridges your private filesystem with Large Language Models, allowing AI to search, read, summarize, create, and organize your documents — with full user control and privacy.
---
✨ Key Features
- 📚 Resource Discovery: Files, folders, and notes exposed as structured MCP Resources.
- 🔎 Smart Search: Search workspace contents by name, path, or keywords.
- 📝 Document Summarization: Quickly summarize meeting notes, articles, or project plans.
- 🗂️ File Creation and Organization: Create, rename, move, and (optionally) delete files.
- ⚙️ Configurable and Secure: Full control over file types, size limits, and writable actions.
- 🔌 MCP Compatible: Connects to any MCP-enabled client without custom integration.
- 🛡️ Local-First Privacy: Your data never leaves your machine.
---
🛠 How It Works
- Runs an MCP-compliant server on your Mac.
- Connects to LLM applications through standard I/O or HTTP (future).
- Represents your workspace directory (e.g., ~/Documents/Workspace) as:
- Resources (files and metadata)
- Tools (search, summarize, create files, etc.)
- Allows the LLM, under user control, to query, analyze, and modify local content.
- All destructive actions (delete, move) are gated behind secure configuration.
---
🏛️ Technical Overview
| Component | Description |
|-----------------|----------------------------------------------|
| MCP Server | Built using the official Python MCP SDK |
| Transport | Stdio (local connections), SSE (planned) |
| Resources | Files (.txt, .md, .pdf) exposed via URIs |
| Tools | JSON-schema validated functions (e.g., search, summarize, create) |
| Configuration | .env file + Command-line overrides |
| Security | Read-only by default, fine-grained tool access control |
---
🚀 Getting Started
Prerequisites
- macOS (Silicon / ARM64)
- Python 3.10+
- Node.js (optional, for testing tools like MCP Inspector)
- MCP-compatible client (e.g., Claude Desktop)
Installation
```bash
Sign in to leave a review
Use Google, GitHub, or an email account so ratings stay tied to real people.
No reviews posted yet.
