sandbox_batch
Execute multiple commands, index all outputs, and run multiple search queries — all in ONE call. This is the highest-efficiency tool: one sandbox_batch replaces N sandbox_execute calls + M sandbox_search calls. Use for research phases, multi-file analysis, or any task requiring multiple data sour...
This record as markdown: /tools/io-github-homenshum-nodebench/sandbox-batch.md
What sandbox_batch does on Nodebench
AI agents invoke sandbox_batch to trigger actions in Nodebench. 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.
Why sandbox_batch is rated High
The tool explicitly allows execution of arbitrary commands in a sandbox environment. While sandboxed execution provides some containment, the ability to run multiple commands sequentially in a single call with indexed outputs creates risk of unintended side effects or command injection. The batch nature amplifies potential impact compared to individual command execution.
From the tool's definition Execute multiple commands, index all outputs, and run multiple search queries — all in ONE call
Attacks that exploit this kind of access
The rule that runs sandbox_batch safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Nodebench, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For sandbox_batch, this is the rule to start with:
sandbox_batch 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 Nodebench, apply this rule, and every sandbox_batch call is checked against it from then on.
Questions about sandbox_batch
Execute multiple commands, index all outputs, and run multiple search queries — all in ONE call. This is the highest-efficiency tool: one sandbox_batch replaces N sandbox_execute calls + M sandbox_search calls. Use for research phases, multi-file analysis, or any task requiring multiple data sources. It is categorised as a Execute tool in the Nodebench MCP Server, which means it can trigger actions or run processes. Use rate limits and argument validation.
Register the Nodebench MCP server in PolicyLayer and add a rule for sandbox_batch: 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 Nodebench. Nothing to install.
sandbox_batch 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 sandbox_batch 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 sandbox_batch. 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.
sandbox_batch is provided by the Nodebench MCP server (nodebench-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Nodebench, and thousands of servers like it.
Across the catalogue