sandbox_stats
Show context savings for the current session — per-tool breakdown, total bytes indexed vs returned, savings ratio, and estimated token savings. Use to quantify how much context window space the sandbox has preserved.
This record as markdown: /tools/io-github-homenshum-nodebench/sandbox-stats.md
What sandbox_stats does on Nodebench
AI agents call sandbox_stats to retrieve information from Nodebench without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why sandbox_stats is rated Low
The tool purely queries and returns statistical information about sandbox context usage. No data is modified, no external operations are triggered, and no irreversible actions occur. This is a straightforward metrics/monitoring retrieval function, falling cleanly into the Read category with low severity since it poses minimal risk if misused by an AI agent.
From the tool's definition Tool name 'sandbox_stats' and description indicating it 'Show[s] context savings for the current session — per-tool breakdown, total bytes indexed vs returned, savings ratio, and estimated token savings.' This is a read-only operation that retrieves and…
Attacks that exploit this kind of access
The rule that runs sandbox_stats 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_stats, this is the rule to start with:
sandbox_stats is read-only, so it stays allowed. 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_stats call is checked against it from then on.
Questions about sandbox_stats
Show context savings for the current session — per-tool breakdown, total bytes indexed vs returned, savings ratio, and estimated token savings. Use to quantify how much context window space the sandbox has preserved. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.
Register the Nodebench MCP server in PolicyLayer and add a rule for sandbox_stats: 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_stats is a Read tool with low risk. Read-only tools are generally safe to allow by default.
Yes. Add a rate_limit block to the sandbox_stats 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_stats. 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_stats 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.
This server
Across the catalogue