Back to directory

AgentDock MCP

AgentDock is a tool runtime that gives AI agents controlled, permissioned access to real computers, servers and containers, so a chat client such as ChatGPT can run commands, edit files, operate Git and manage Docker services across several connected machines in one conversation.

AgentDock MCP

AgentDock is an independent tool runtime for AI agents. It gives an agent unified, secure and controlled access to files, commands, Git, Skills, MCP tools, browser automation and task execution across local computers, remote servers and containers, and it does not provide a chat interface or run model inference itself.

Through it, a client such as ChatGPT can manage multiple computers and servers without repeatedly switching SSH sessions, write code and run tests in the real environment, manage VPS hosts, Docker services and reverse proxies, inspect logs, processes and ports, operate authenticated web pages and macOS applications, and coordinate cross-device work by connecting several AgentDock instances together. It installs from official packages for Docker, Linux, macOS and Windows.

More in MCP servers

See all 734
  • Light Cloud

    light-cloud.com

    A hosting platform that deploys a static site, a container, or a managed Postgres database straight from a GitHub, GitLab, or Bitbucket push, with a preview URL for every branch and an MCP server for deploying from Claude Code.

  • ForensicDbg

    forensicdbg.com

    A post-mortem debugger for native Windows x86 and x64 crashes, with an MCP interface so AI tools can consume crash-dump analysis directly.

  • Karada.ai

    karada.ai

    A CI/CD platform that auto-compiles existing APIs into Go MCP servers, attaches composable middleware, and exposes them through one gateway usable from Cursor, Claude Code, and Windsurf.