sandboxes_agent_tasks_create

Run sandboxes.agent-tasks.create through the Appaloft application operation catalog. Shared with CLI and HTTP/API.

SERVERAppaloft SOURCE@appaloft/mcp

Medium RISK CLASS

Category Write

Parameters 114 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/appaloft-mcp/sandboxes-agent-tasks-create.md

WHAT IT DOES

What sandboxes_agent_tasks_create does on Appaloft

AI agents use sandboxes_agent_tasks_create to create or update resources in Appaloft, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Appaloft environment.

Parameter	Type	Required
`task`	string	Yes
`checks`	array	—
`preview`	object	—
`runtimeId`	string	Yes
`runContext`	object	—
`sourceRoot`	string	—
`workspaceId`	string	Yes
`idempotencyKey`	string	Yes
`immutableReview`	boolean	—
`nativeSessionCapable`	boolean	—
`nativeAgentSessionRef`	string	—

Parameters from the server's own tool schema.

RISK

Why sandboxes_agent_tasks_create is rated Medium

An AI agent can call sandboxes_agent_tasks_create faster than any human can review: one bad instruction and it creates or modifies resources in Appaloft by the hundred, each call as confident as the last.

Risk signalsHigh parameter count (18 properties)

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs sandboxes_agent_tasks_create safely

PolicyLayer is an MCP gateway: it sits between your AI agents and Appaloft, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sandboxes_agent_tasks_create, this is the rule to start with:

sandboxes_agent_tasks_create Rate-limited

sandboxes_agent_tasks_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.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sandboxes_agent_tasks_create": {
      "limits": [
        {
          "counter": "sandboxes_agent_tasks_create_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Appaloft, apply this rule, and every sandboxes_agent_tasks_create call is checked against it from then on.

FAQ

Questions about sandboxes_agent_tasks_create

What does the sandboxes_agent_tasks_create tool do? +

Run sandboxes.agent-tasks.create through the Appaloft application operation catalog. Shared with CLI and HTTP/API. It is categorised as a Write tool in the Appaloft MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

What parameters does sandboxes_agent_tasks_create accept? +

sandboxes_agent_tasks_create accepts 11 parameters: task, checks, preview, runtimeId, runContext, sourceRoot, workspaceId, idempotencyKey, immutableReview, nativeSessionCapable, nativeAgentSessionRef. Required: task, runtimeId, workspaceId, idempotencyKey. The full parameter table on this page comes from the server's own tool schema.

How do I enforce a policy on sandboxes_agent_tasks_create? +

Register the Appaloft MCP server in PolicyLayer and add a rule for sandboxes_agent_tasks_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 Appaloft. Nothing to install.

What risk level is sandboxes_agent_tasks_create? +

sandboxes_agent_tasks_create is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sandboxes_agent_tasks_create? +

Yes. Add a rate_limit block to the sandboxes_agent_tasks_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.

How do I block sandboxes_agent_tasks_create completely? +

Set action: deny in the PolicyLayer policy for sandboxes_agent_tasks_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.

What MCP server provides sandboxes_agent_tasks_create? +

sandboxes_agent_tasks_create is provided by the Appaloft MCP server (@appaloft/mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.

KEEP EXPLORING

More on Appaloft, and thousands of servers like it.

This server

All 428 Appaloft tools →

Across the catalogue

create_task on 0rca Dojo MCP Server →create-task on Kanban MCP Server →create_package_backup on Android Forensics ADB MCP Server →create_project on Stitch MCP Server → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →