mcpField
S
spacesentinel-mcp

spacesentinel-mcp

Local
github.com/SheldonZhuangFiles & Storage1Updated 12w ago
Repository

About spacesentinel-mcp

spacesentinel-mcp is an MCP server for conversational disk cleanup and device-cleanup guidance. Its Windows cleanup is limited to whitelisted locations, while disk analysis provides evidence for decisions that remain with the user.

Key features

  1. 01Read-only scan of 13 junk categories
  2. 02Clean whitelisted Windows locations with confirmation
  3. 03Analyze disk usage and ownership evidence
  4. 04Cleanup guides for Windows, Mac, iOS, and Android
  5. 05Guides available in seven languages

Use cases

  1. 01Identify reclaimable space on Windows
  2. 02Clean approved temporary files and caches
  3. 03Review directory evidence before deciding what to delete
  4. 04Get device cleanup steps in supported languages

MCP support

Exposes Windows junk scanning, cleanup, and disk analysis tools, plus multilingual device cleanup guides to MCP clients. Cleanup requires explicit user approval and confirmation.

Configuration

Local server config is the same for every client. Copy it into your client’s MCP config file.

mcp.json · Universal config
{
  "mcpServers": {
    "sheldonzhuang-spacesentinel": {
      "command": "npx",
      "args": [
        "-y",
        "spacesentinel-mcp"
      ]
    }
  }
}
Run commandnpx -y spacesentinel-mcp

Local servers need a runtime on your machine (e.g. Node.js 18+). Config file locations differ by client; see your client’s docs.

Packages
npmspacesentinel-mcp0.1.4

Tools

4

Saved tool list · updated 2w ago

This tool takes no parameters.

Details

From the project README

spacesentinel-mcp

MCP server for SpaceSentinel — conversational disk cleanup for AI agents (Claude Desktop, Cursor, etc.).

Tools

ToolPlatformDescription
scan_junkWindowsRead-only scan of 13 whitelisted junk categories, reports reclaimable size
clean_junkWindowsCleans the whitelist (requires confirm=true after explicit user approval)
analyze_diskWindowsRead-only disk-ownership analysis: per-directory evidence (size, PATH refs, running processes, installed-app registry, known-software signatures) so the AI can reason about what's safe to delete — the user always decides
get_cleanup_guideAllStep-by-step cleanup guide for windows/mac/ios/android in 7 languages

Safety: only whitelisted paths are ever touched (temp files, caches, Recycle Bin) — never Documents, Desktop, Downloads or Photos. The underlying PowerShell tool is open source with Pester test coverage, including deletion-escape defenses.

Setup (Claude Desktop)

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "spacesentinel": {
      "command": "npx",
      "args": ["-y", "spacesentinel-mcp"]
    }
  }
}

Or from a local clone:

{
  "mcpServers": {
    "spacesentinel": {
      "command": "node",
      "args": ["D:/path/to/SpaceSentinel/mcp/index.js"]
    }
  }
}

Then ask your agent: "扫描一下我电脑上的垃圾" / "How do I free up space on my iPhone?"

Development

npm install
node test-mcp.mjs   # protocol-level smoke test (initialize → tools/list → calls)

guides.json and CleanMyPC.ps1 are copied from the repo root — regenerate with node ../tools/build-api.js && cp ../api/guides.json guides.json && cp ../tools/CleanMyPC.ps1 CleanMyPC.ps1 after upstream changes.

MIT © SheldonZhuang

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.