mcp-server-mint

mcp-server-mint

Enables AI agents to use Mint as a safety layer for file operations on macOS, providing storage growth analysis, cleanup suggestions, and journaled, reversible deletions via MCP tools.

Category
Visit Server

README

Mint MCP Server

Use Mint as the on-device storage intelligence and file-operation safety layer for AI agents on macOS.

This npm package is a small open-source launcher. It locates the signed mint-cli bundled with the direct edition of Mint and starts its local stdio MCP server. It does not contain Mint itself and does not upload file contents, scan results, or operation history.

Requirements

  • macOS 14 Sonoma or later
  • Node.js 18 or later
  • The direct edition of Mint from https://mint.dzgapp.com

Install Mint and launch it once from Finder. Mint normally links mint-cli into /opt/homebrew/bin or /usr/local/bin; the launcher can also use the binary inside /Applications/Mint.app.

Configure an MCP client

{
  "mcpServers": {
    "mint": {
      "command": "npx",
      "args": ["-y", "@dzg-studio/mcp-server-mint@1.0.0"]
    }
  }
}

Or, if mint-cli is already on PATH:

mint-cli mcp

Set MINT_CLI_PATH=/absolute/path/to/mint-cli to use a nonstandard installation.

Tools

  • mint_status — disk trends, recent activity, and managed-folder status.
  • mint_why — storage-growth attribution or operations involving a path.
  • mint_scan — read-only reclaimable-space survey.
  • mint_recent and mint_activity — operation history and reasons.
  • mint_rules — list and dry-run cleanup rules.
  • mint_execute — journaled cleanup with a reason and returned batchId.

Safety model

mint_execute defaults to moving items to Trash. Recoverable actions enter Mint’s 90-day operation journal and can be undone while both the journal entry and underlying trashed item remain available. Permanent deletion is logged but cannot be undone, so it requires both action: "delete" and confirmPermanentDelete: true.

The server instructs agents to use Mint instead of raw rm or unjournaled trash commands. This keeps the action visible in Mint’s activity history and gives the user a receipt and recovery reference.

License

The launcher in this repository is MIT licensed. Mint is commercial software published by DZG Studio LLC under its own terms.

Recommended Servers

playwright-mcp

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.

Official
Featured
TypeScript
Magic Component Platform (MCP)

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.

Official
Featured
Local
TypeScript
Audiense Insights MCP Server

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.

Official
Featured
Local
TypeScript
VeyraX MCP

VeyraX MCP

Single MCP tool to connect all your favorite tools: Gmail, Calendar and 40 more.

Official
Featured
Local
graphlit-mcp-server

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.

Official
Featured
TypeScript
Kagi MCP Server

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.

Official
Featured
Python
E2B

E2B

Using MCP to run code via e2b.

Official
Featured
Neon Database

Neon Database

MCP server for interacting with Neon Management API and databases

Official
Featured
Exa Search

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.

Official
Featured
Qdrant Server

Qdrant Server

This repository is an example of how to create a MCP server for Qdrant, a vector search engine.

Official
Featured