Disk Insights MCP
A read-only MCP server that reports largest files, folder sizes, and disk usage, running locally without any data leaving your machine.
README
Disk Insights MCP
Ask Claude Desktop "what's eating my disk space?" — and get a real answer.
A tiny, read-only Model Context Protocol server. It reports your largest files and most bloated folders. It never deletes, moves, or modifies anything, and wide scans are time-bounded so they return useful results instead of hanging.
Runs 100% locally. Nothing leaves your machine.
What it does
| Tool | What you ask Claude | What you get |
|---|---|---|
largest_files |
"What are the biggest files in my Downloads?" | Top N files by size |
folder_sizes |
"Which folders in my home dir are biggest?" | Sub-folders ranked by total size |
disk_usage |
"How full is my disk?" | Total / used / free for the volume |
All read-only. All offline.
Install (2 minutes)
Requirements: Python 3.10+ and the Claude Desktop app.
pip install "mcp[cli]"
Download disk_insights_mcp.py from this repo, then add it to your Claude Desktop
config:
- macOS:
~/Library/Application Support/Claude/claude_desktop_config.json - Windows:
%APPDATA%\Claude\claude_desktop_config.json
{
"mcpServers": {
"disk-insights": {
"command": "python3",
"args": ["/full/path/to/disk_insights_mcp.py"]
}
}
}
Restart Claude Desktop. Then just ask: "What's taking up space in my Downloads folder?"
A ready-to-edit claude_desktop_config.example.json is included.
Why read-only?
Disk cleanup tools that can delete files are exactly the tools you don't want an LLM driving unsupervised. This server only reports. You stay in control of what to remove.
Want the rest?
Disk Insights is one server from the MCP Starter Kit — a set of local-first servers for Claude Desktop, all MIT licensed:
- Doc Search — index a folder and search across everything, including the text inside PDFs and DOCX, fully offline (SQLite FTS5, no gigabyte model to download).
- Obsidian Vault — read/write/search/link notes in a local Obsidian vault.
- Git Companion — status, diffs, log, blame, and drafts real commit messages (commits require explicit confirm, never pushes).
- Plus File Manager, Web Scraper, SQLite, PDF Export and Notes in the original kit.
One-click installers for macOS/Linux/Windows, clean uninstaller, full docs: https://kuhnrichard.gumroad.com/l/kpllrc
Everything is MIT — you can always build your own from servers like this one.
License
MIT © Richard Kuhn — blog.kuhn.or.at
Recommended Servers
playwright-mcp
A Model Context Protocol server that enables LLMs to interact with web pages through structured accessibility snapshots without requiring vision models or screenshots.
Magic Component Platform (MCP)
An AI-powered tool that generates modern UI components from natural language descriptions, integrating with popular IDEs to streamline UI development workflow.
Audiense Insights MCP Server
Enables interaction with Audiense Insights accounts via the Model Context Protocol, facilitating the extraction and analysis of marketing insights and audience data including demographics, behavior, and influencer engagement.
VeyraX MCP
Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.
graphlit-mcp-server
The Model Context Protocol (MCP) Server enables integration between MCP clients and the Graphlit service. Ingest anything from Slack to Gmail to podcast feeds, in addition to web crawling, into a Graphlit project - and then retrieve relevant contents from the MCP client.
Kagi MCP Server
An MCP server that integrates Kagi search capabilities with Claude AI, enabling Claude to perform real-time web searches when answering questions that require up-to-date information.
E2B
Using MCP to run code via e2b.
Neon Database
MCP server for interacting with Neon Management API and databases
Exa Search
A Model Context Protocol (MCP) server lets AI assistants like Claude use the Exa AI Search API for web searches. This setup allows AI models to get real-time web information in a safe and controlled way.
Qdrant Server
This repository is an example of how to create a MCP server for Qdrant, a vector search engine.