adaptercloud_sandbox_create
Create a new Kubernetes-native sandbox environment with Kata Containers isolation.
This record as markdown: /tools/burdenoff-adaptercloud-mcp/adaptercloud-sandbox-create.md
What adaptercloud_sandbox_create does on Adaptercloud
AI agents use adaptercloud_sandbox_create to create or update resources in Adaptercloud, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Adaptercloud environment.
| Parameter | Type | Required | Description |
|---|---|---|---|
mode | string | — | Run mode: DEPLOYMENT (long-running) or JOB (run-to-completion) |
name | string | Yes | Sandbox name |
template | string | Yes | Sandbox template type |
resources | object | — | Resource requests/limits |
containers | array | — | Container specifications (uses template defaults if omitted) |
templateId | string | — | Sandbox template config ID to use |
ttlSeconds | number | — | Time-to-live in seconds |
description | string | — | Sandbox description |
Parameters from the server's own tool schema.
Why adaptercloud_sandbox_create is rated Medium
An AI agent can call adaptercloud_sandbox_create faster than any human can review: one bad instruction and it creates or modifies resources in Adaptercloud by the hundred, each call as confident as the last.
Risk signalsAccepts raw HTML/template content (template) · High parameter count (23 properties)
Attacks that exploit this kind of access
The rule that runs adaptercloud_sandbox_create safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Adaptercloud, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For adaptercloud_sandbox_create, this is the rule to start with:
adaptercloud_sandbox_create stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Adaptercloud, apply this rule, and every adaptercloud_sandbox_create call is checked against it from then on.
Questions about adaptercloud_sandbox_create
Create a new Kubernetes-native sandbox environment with Kata Containers isolation. It is categorised as a Write tool in the Adaptercloud MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
adaptercloud_sandbox_create accepts 8 parameters: mode, name, template, resources, containers, templateId, ttlSeconds, description. Required: name, template. The full parameter table on this page comes from the server's own tool schema.
Register the Adaptercloud MCP server in PolicyLayer and add a rule for adaptercloud_sandbox_create: allow, deny, rate-limit, or require approval. Point your MCP client at the PolicyLayer proxy URL and the rule is enforced on every call, before it reaches Adaptercloud. Nothing to install.
adaptercloud_sandbox_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the adaptercloud_sandbox_create rule in your PolicyLayer policy. For example, setting max: 10 and window: 60 limits the tool to 10 calls per minute. Rate limits are tracked per agent session and reset automatically.
Set action: deny in the PolicyLayer policy for adaptercloud_sandbox_create. The AI agent will receive a policy violation error and cannot call the tool. You can also include a reason field to explain why the tool is blocked.
adaptercloud_sandbox_create is provided by the Adaptercloud MCP server (@burdenoff/adaptercloud-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Adaptercloud, and thousands of servers like it.
This server
Across the catalogue