# Agent VM

> Use this tool when you need to securely execute Linux commands and access filesystems in a sandboxed environment. Agent VM solves problems related to secure file management and command execution, providing a standardized HTTP interface for inputs and outputs. It is ideal for use cases requiring isolated and auditable Linux operations, with configurable security modes and comprehensive logging.

Canonical page: https://skillsregistry.net/skills/gh-sean-lai-sh-agent-vm  
JSON: https://api.skillsregistry.net/v1/skills/gh-sean-lai-sh-agent-vm

## Description

Agent VM provides a Docker-based sandboxed Linux environment with filesystem and shell access exposed through a standard MCP Streamable HTTP interface. The embedded resolver offers file listing, reading with automatic chunking for large files, writing with auto-created parent directories, and shell command execution with real-time SSE streaming of output. Security is enforced through seven independent layers including configurable security modes (strict, moderate, permissive), command whitelisting and blacklisting, argument validation, direct execution without shell interpretation, and comprehensive audit logging.

## Trust

- **Trust score (0–1):** 0.81
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/gh-sean-lai-sh-agent-vm)
- **Repository:** <https://github.com/sean-lai-sh/agent-vm>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "gh-sean-lai-sh-agent-vm"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gh-sean-lai-sh-agent-vm` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gh-sean-lai-sh-agent-vm/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt