agentdock
View on GitHubSecure MCP runtime for AI agents to operate local machines, servers, and containers with multi-device orchestration.
AgentDock is a self-hosted Go MCP runtime that gives AI agents permission-bounded access to files, shells, Git, browsers and containers on local machines, VPS hosts and Docker. It exposes tools over MCP Streamable HTTP with OAuth/Bearer auth and supports multi-device orchestration and Skills.
Use Cases
Operate local machines, remote servers and containers from one AI chat via MCPRun shell commands, edit files and manage Git in real environmentsManage VPS hosts, Docker services and reverse proxiesInspect logs, processes, ports and runtime stateBrowser and macOS desktop automation with persistent loginCoordinate multi-device workflows across multiple AgentDock instancesInstall and manage Agent Skills and dynamic MCP serversPersist and resume long-running agent tasks with checkpoints
Built With
- Language
- Go
- Frameworks
- modelcontextprotocol/go-sdk · chromedp · gorilla/websocket · go-oauth2 · Docker · jsonschema
Tags
mcp · mcp-server · ai-agents · remote-control · self-hosted · docker · devops · automation · tool-calling · agent-skills · browser-automation · pty · oauth · go · multi-device · streamable-http