agentdock

Provides a secure, controlled local machine, server, and container operating environment for AI agents.

MCPDevOpen source

Type: MCP
Transport: http
Open source: Yes
GitHub Stars: ★ 1.0k
Source: mcp-github
Repository: github.com/uvwt/agentdock

Overview

AgentDock is a standalone runtime that offers AI agents unified, secure, and controlled capabilities for file management, command execution, Git operations, skills, MCP, browser automation, and task execution. It supports coordination across local machines, remote servers, and containers, enabling multi-device workflows within a single conversation. AgentDock does not provide a chat interface or model inference; instead, it focuses on enabling AI agents to operate within well-defined permission boundaries in real environments, returning structured, traceable, and verifiable results.

Capabilities

▪Manage multiple computers and servers
▪Write code, modify projects, run tests, and manage Git
▪Manage VPS hosts, Docker services, reverse proxies, and deployment configurations
▪Check logs, processes, ports, and actual running states
▪Interact with authenticated web pages and macOS desktop applications
▪Connect multiple AgentDock instances and coordinate cross-device workflows

Use cases

Manage multiple computers and servers via ChatGPTWrite and run code in real environmentsManage and deploy VPS and Docker servicesCoordinate tasks across devices

Setup

Requires: API KeyNode 环境

Install from the official package: https://uvwt.github.io/agentdock-docs/docs/getting-started/install

This information was compiled by AI from public sources and may contain inaccuracies — please refer to the source.

FAQ

Which platforms does AgentDock support?

Supports macOS, Linux, Windows, and containers.

How do I connect an AI client?

Use MCP Streamable HTTP to configure the client.

Related skills

answer-me-with-html

Let an AI Agent answer complex questions with a single HTML page.

Agent Skill

sast-skills

Transform your AI coding assistant into a SAST scanner to automatically detect vulnerabilities in code.

Agent Skill

Lightswind-UI-Library

AI-native CLI-first React component library with MCP Server support.

MCP

scientific-agent-skills

Transform any AI agent into a scientific assistant with 147 ready-to-use research skills.

Agent Skill

susi_alexa_skill

A skill that enables question-and-answer interactions between Alexa and Susi AI.

Agent Skill

claude-context

Provides code search capabilities for Claude Code, turning the entire codebase into context.

MCP