gantry — security grade SAFE, quality 69/100

Security audit verdict: SAFE · quality 69/100

No red flags found in any of the 11 categories — no credential harvesting, no data exfiltration, no curl-pipe-shell installer. Scanned against the SlowMist agent-security taxonomy, refreshed every 8 hours. Full audit →

by getgantry · MCP Server · ★ 55

Last updated: · Indexed by AgentSkillsHub · Auto-synced every 8h

🔒 Is gantry safe to install? View the security audit →

About gantry

Gantry Native Docker management for your Mac. Local and over SSH. Agent-ready with a built-in MCP server. Free, open source, no limits. Gantry is a fully native macOS app (SwiftUI, Swift 6) for managing and monitoring Docker — the local daemon and any number of remote hosts over SSH — plus apple/container hosts on your Mac. No Electron, no subscription, no artificial limits. It is built to be driven by AI agents too: a bundled MCP server and App Intents expose your Docker hosts to Claude, Shortcuts, Siri and scripts. Website: https://getgantry.github.io/ Features Core Containers — list, inspect, start/stop/restart/kill/pause, rename, remove, create and run with ports/env/volumes/restart-policy, commit to image, export filesystem, view processes (), update restart policy Images — list, history, tag, pu

ai-agentscontainersdeveloper-toolsdockermacosmcpmcp-serversshswiftswiftui

Quick Facts

Stars55
Forks3
LanguageSwift
CategoryMCP Server
LicenseMIT
Quality Score68.537577796822/100
Open Issues3
Last Updated2026-08-10
Created2026-06-04
Platformsdocker, mcp
Est. Tokens~18k

Compatible Skills

These tools work well together with gantry for enhanced workflows:

gantry alternative? Top 6 similar tools

Looking for a gantry alternative? If you're comparing gantry with other mcp server tools, these 6 projects are the closest alternatives on Agent Skills Hub — ranked by topic overlap, star count, and community traction.

  • xclaude-plugin by conorluddy · ⭐ 182

    iOS development ClaudeCode plugin for mindful token and context usage. Contains modular MCPs that group variou

  • toolhive-studio by stacklok · ⭐ 167

    ToolHive is an application that allows you to install, manage and run MCP servers and connect them to AI agent

  • vibepod-cli by VibePod · ⭐ 165

    Unified CLI for running AI coding agents in isolated containers. Includes built-in local metrics collection, H

  • claude-emporium by Vvkmnn · ⭐ 82

    🏛 [UNDER CONSTRUCTION] A (roman) claude plugin marketplace

  • cronstable by ptweezy · ⭐ 80

    A modern, container-friendly, optionally-distributed, fault-tolerant, highly available, leader-electing, highl

  • google-analytics-mcp by surendranb · ⭐ 242

    Google Analytics 4 data to AI agents, agentic workflows, and MCP clients. Give agents analysis-ready access to

More MCP Server Tools

Explore other popular mcp server tools:

View all MCP Server tools →

Popular Swift Agent Tools

Frequently Asked Questions

What is gantry?

gantry is Native macOS app for managing and monitoring Docker — local and over SSH. Agent-ready: built-in MCP server and App Intents. Free and open source.. It is categorized as a MCP Server with 55 GitHub stars.

What programming language is gantry written in?

gantry is primarily written in Swift. It covers topics such as ai-agents, containers, developer-tools.

How do I install or use gantry?

You can find installation instructions and usage details in the gantry GitHub repository at github.com/getgantry/gantry. The project has 55 stars and 3 forks, indicating an active community.

What license does gantry use?

gantry is released under the MIT license, making it free to use and modify according to the license terms.

What are the best alternatives to gantry?

The top alternatives to gantry on Agent Skills Hub include xclaude-plugin, toolhive-studio, vibepod-cli. Each offers a different approach to the same problem space — compare them side-by-side by stars, quality score, and community activity.

How this security grade is produced

Grades come from a rule-based scan built on the SlowMist agent-security taxonomy, covering 11 red-flag categories including credential harvesting, data exfiltration, and curl | sh installers. It is a first-layer scan, not a manual audit — we say so rather than overstate it.

The scale of the problem is documented independently: Liu et al. (2026), in a study of 31,132 agent skills, report that 26.1% contain security vulnerabilities. Our own full-catalog census is published as a citable open dataset.

Sources & who's responsible:

View on GitHub → Browse MCP Server tools