sandboxes_agents_runs_create
Run sandboxes.agents.runs.create through the Appaloft application operation catalog. Shared with CLI and HTTP/API.
This record as markdown: /tools/appaloft-mcp/sandboxes-agents-runs-create.md
What sandboxes_agents_runs_create does on Appaloft
AI agents invoke sandboxes_agents_runs_create to trigger actions in Appaloft. What it does depends on the arguments the agent supplies, and its effects often reach beyond the immediate call: builds kicked off, notifications sent, workflows started.
| Parameter | Type | Required | Description |
|---|---|---|---|
task | string | Yes | |
context | object | Yes | |
runtimeId | string | Yes | |
sandboxId | string | Yes | |
idempotencyKey | string | Yes |
Parameters from the server's own tool schema.
Why sandboxes_agents_runs_create is rated High
The tool creates and executes agent runs inside sandboxes, which constitutes running external operations or code. The 'sandbox' and 'agents.runs' nomenclature strongly implies code/process execution. Severity is high because misconfigured or malicious agent runs inside sandboxes can have significant impact on the system or data.
From the tool's definition 'runs_create' and 'Run sandboxes.agents.runs.create' indicate execution of agent runs within sandboxes
Attacks that exploit this kind of access
The rule that runs sandboxes_agents_runs_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_agents_runs_create, this is the rule to start with:
sandboxes_agents_runs_create stays usable, but rate-capped: a runaway agent can't fire it dozens of times a minute. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Appaloft, apply this rule, and every sandboxes_agents_runs_create call is checked against it from then on.
Questions about sandboxes_agents_runs_create
Run sandboxes.agents.runs.create through the Appaloft application operation catalog. Shared with CLI and HTTP/API. It is categorised as a Execute tool in the Appaloft MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
sandboxes_agents_runs_create accepts 5 parameters: task, context, runtimeId, sandboxId, idempotencyKey. Required: task, context, runtimeId, sandboxId, idempotencyKey. The full parameter table on this page comes from the server's own tool schema.
Register the Appaloft MCP server in PolicyLayer and add a rule for sandboxes_agents_runs_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.
sandboxes_agents_runs_create is a Execute tool with high risk. Execute tools should be rate-limited and have argument validation enabled.
Yes. Add a rate_limit block to the sandboxes_agents_runs_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 sandboxes_agents_runs_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.
sandboxes_agents_runs_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.
More on Appaloft, and thousands of servers like it.
Across the catalogue