MCP server for DiskCleanKit - One Touch Scan and Clean for Mac
Config is the same across clients — only the file and path differ.
{
"mcpServers": {
"diskcleankit": {
"args": [
"@vannamtran/diskcleankit-mcp"
],
"command": "npx"
}
}
}Are you the author?
Add this badge to your README to show your security score and help users find safe servers.
MCP (Model Context Protocol) server that enables AI assistants like Claude to control DiskCleanKit's One Touch feature for Mac disk cleaning.
Run this in your terminal to verify the server starts. Then let us know if it worked — your result helps other developers.
npx -y '@vannamtran/diskcleankit-mcp' 2>&1 | head -1 && echo "✓ Server started successfully"
After testing, let us know if it worked:
Five weighted categories — click any category to see the underlying evidence.
No known CVEs.
Checked @vannamtran/diskcleankit-mcp against OSV.dev.
Click any tool to inspect its schema.
Be the first to review
Have you used this server?
Share your experience — it helps other developers decide.
Sign in to write a review.
Others in productivity
Persistent memory using a knowledge graph
Dynamic problem-solving through sequential thought chains
mini cli search engine for your docs, knowledge bases, meeting notes, whatever. Tracking current sota approaches while being all local
Official Miro MCP server - Supports context to code and creating diagrams, docs, and data tables.
MCP Security Weekly
Get CVE alerts and security updates for io.github.namtran/diskcleankit-mcp and similar servers.
Start a conversation
Ask a question, share a tip, or report an issue.
Sign in to join the discussion.
MCP (Model Context Protocol) server that enables AI assistants like Claude to control DiskCleanKit's One Touch feature for Mac disk cleaning.
npm install -g @vannamtran/diskcleankit-mcp
git clone https://github.com/namtran/diskcleankit-mcp
cd diskcleankit-mcp
npm install
npm run build
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"diskcleankit": {
"command": "npx",
"args": ["@vannamtran/diskcleankit-mcp"]
}
}
}
Then restart Claude Desktop.
claude mcp add --transport stdio diskcleankit -- npx @vannamtran/diskcleankit-mcp
Or edit ~/.claude/settings.json:
{
"mcpServers": {
"diskcleankit": {
"command": "npx",
"args": ["@vannamtran/diskcleankit-mcp"]
}
}
}
Add to ~/.cursor/mcp.json (global) or .cursor/mcp.json (project-specific):
{
"mcpServers": {
"diskcleankit": {
"command": "npx",
"args": ["@vannamtran/diskcleankit-mcp"]
}
}
}
Or go to Cursor Settings → Tools & Integrations → New MCP Server.
Add to your settings.json:
{
"mcp.servers": {
"diskcleankit": {
"command": "npx",
"args": ["@vannamtran/diskcleankit-mcp"]
}
}
}
| Client | Config File |
|---|---|
| Cline | VS Code extension settings |
| Windsurf | ~/.windsurf/mcp.json |
| Zed | ~/.config/zed/settings.json |
| Continue | ~/.continue/config.json |
Use the same configuration structure:
{
"mcpServers": {
"diskcleankit": {
"command": "npx",
"args": ["@vannamtran/diskcleankit-mcp"]
}
}
}
Ollama doesn't natively support MCP, but you can use mcphost:
pip install mcphost
mcphost -m ollama:qwen2.5 --config config.json
| Tool | Description |
|---|---|
one_touch_scan | Scan for junk files (safe, no deletion) |
one_touch_clean | Recommended - Scan AND clean junk files automatically |
get_disk_status | Check disk space and health status |
get_cleanable_estimate | Estimate cleanable space by category |
get_cleaning_history | View past cleaning sessions |
one_touch_clean automatically scans and cleans safe items only:
| Category | Description |
|---|---|
| System Caches | macOS system cache files |
| Application Caches | App-generated cache files |
| Application Logs | Old log files from apps |
| Browser Caches | Safari, Chrome, Firefox cache |
These are all safe to delete and will be regenerated by the system/apps as needed.
Once configured, ask your AI assistant:
one_touch_scanone_touch_cleanget_disk_statusget_cleanable_estimateget_cleaning_historyAI Assistant → MCP Server → URL Scheme → DiskCleanKit App
↑ ↓
JSON Response ← Temp File ← Response
diskcleankit:// URL scheme/tmp/diskcleankit_mcp_response.json