Skip to main content
Glama

vm_create

Creates an isolated Ubuntu sandbox with Chrome, VNC, and xfce4 for AI computer tasks. Supports resuming from saved snapshots. Returns a sandbox ID and noVNC URL to monitor activity.

Instructions

Create a new sandbox (isolated Ubuntu mini-computer with shell, Chrome + CDP, VNC, xfce4). IMPORTANT: Before creating, check if the user has saved snapshots by looking at the available_snapshots field in the response. If snapshots exist, ask the user whether they want to resume from a snapshot or start fresh. Set use_snapshot: true to resume. Backend is auto-detected: Firecracker microVM if KVM available, Docker otherwise. Returns the sandbox id used by all other tools, plus a noVNC URL the human can open to watch what the AI is doing. IMPORTANT: Always present vnc_url exactly as returned — never modify the URL path, filename, or query parameters.

Input Schema

TableJSON Schema
NameRequiredDescriptionDefault
labelYesA descriptive name for this VM chosen by the user. IMPORTANT: Always ask the user what they want to name their VM before creating it. Do not auto-generate names.
extra_portsNoAdditional guest ports to expose on the host (e.g. [3000, 8080]). Each gets a unique host port.
profile_dirNoOptional host path to mount as the Chrome profile dir (e.g. ~/.taw-computer/profile). Persists cookies, logged-in Gmail, etc. across containers.
use_snapshotNoSet to true to resume from a previously saved snapshot with the same label. If false or omitted, creates a fresh VM from the base image.
Behavior4/5

Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?

No annotations present, so description carries full burden. Discloses backend auto-detection, return values (sandbox id, VNC URL), and snapshot resumption behavior. Could mention cleanup or error handling.

Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.

Conciseness4/5

Is the description appropriately sized, front-loaded, and free of redundancy?

Well-structured with important points upfront and critical warnings (IMPORTANT). Slightly verbose with repeated emphasis but overall concise for the complexity.

Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.

Completeness4/5

Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?

Covers creation process, snapshot handling, backend selection, return values, and URL usage. Lacks error conditions or rate limits, but adequate for a creation tool with no output schema.

Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.

Parameters4/5

Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?

Schema coverage is 100% (baseline 3). Description adds meaningful context: label must be user-chosen, extra_ports exposes guest ports, use_snapshot resumes from snapshot. Enhances understanding beyond schema.

Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.

Purpose5/5

Does the description clearly state what the tool does and how it differs from similar tools?

Clearly states 'Create a new sandbox' with specific verb and resource. Distinguishes from sibling tools like vm_list and vm_destroy by focusing on creation and returning an ID used by other tools.

Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.

Usage Guidelines4/5

Does the description explain when to use this tool, when not to, or what alternatives exist?

Provides explicit guidance: check snapshots before creating, ask user about resuming, present VNC URL as-is. Lacks explicit alternative tool references but sibling list provides context.

Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.

Install Server

Other Tools

Latest Blog Posts

MCP directory API

We provide all the information about MCP servers via our MCP API.

curl -X GET 'https://glama.ai/api/mcp/v1/servers/tawgroup/taw-computer'

If you have feedback or need assistance with the MCP directory API, please join our Discord server