agent-vm-mcp
Related Servers
Alternatives to agent-vm-mcp
No user-submitted related servers found.
Related Servers
- FlicenseNot gradedqualityCmaintenanceEnables AI agents to operate a persistent Linux sandbox in the cloud, running commands, managing files, using Git, and publishing artifacts through a Streamable HTTP MCP endpoint.-
- AlicenseNot gradedqualityAmaintenanceEnables AI clients to securely operate isolated coding workspaces with file, command, Git, and deployment tools via authenticated remote MCP.8MIT
- AlicenseNot gradedqualityBmaintenanceEnables MCP clients such as ChatGPT and Claude to administer Linux or macOS hosts through authenticated Streamable HTTP, including running shell commands, reading and writing files within a workspace, listing directories, and retrieving system metrics.MIT
- AlicenseNot gradedqualityBmaintenanceEnables any MCP client to read, search, patch, and execute commands in a codebase, including interactive sessions and git operations, with permission modes and safety boundaries.Apache 2.0
- AlicenseAqualityBmaintenanceSelf-hosted MCP server that gives AI assistants a real Linux development environment: file editing, shell commands, tmux terminals, and browser screenshots, with bounded access through a project registry and write gates.39MIT
- AlicenseNot gradedqualityBmaintenanceEnables AI clients to operate on a remote Linux server over MCP, allowing shell command execution, file editing, package installation, project builds, and service management.MIT
TDQS
Scored across 27 tools
Tool purposes are largely distinct: exec vs process_start vs agent_start have explicit boundary guidance, and agent_* lifecycle tools map to unique operations. Minor overlap remains between capabilities and agent_capabilities, and agent_get/agent_read are somewhat close, but descriptions clarify intent.
A clear noun_verb/prefix pattern dominates (workspace_*, agent_*, process_*), but there are deviations: exec, read_file, import_file, present_file, apply_patch, and command_info use a different verb-first style, and the bare capabilities tool mixes conventions.
27 tools is heavy for a VM execution server, exceeding the 25-tool threshold. The large agent_* cluster plus separate process_* lifecycle families adds surface area and cognitive load, though each tool does earn some place.
Strong lifecycle coverage: file read/import/present, workspace CRUD, process start/read/write/kill/list, and full agent start/get/read/prompt/suspend/resume/stop. Minor gaps exist, such as no file write/delete counterpart to read_file and no explicit directory-creation or move operation.