smart_select_tools
LLM-powered tool selection: sends your task description + a compact tool catalog to a fast model (Gemini 3 Flash, GPT-5-mini, or Claude Haiku 4.5) to pick the best 5-10 tools. Much more accurate than keyword search for ambiguous queries like
This record as markdown: /tools/io-github-homenshum-nodebench/smart-select-tools.md
What smart_select_tools does on Nodebench
AI agents invoke smart_select_tools 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 smart_select_tools is rated High
This tool invokes external AI model APIs (Gemini, GPT, Claude) with user-provided content, triggering external operations whose effects depend on arguments. It is not a simple read — it actively calls third-party LLM services and influences downstream tool selection, which could cascade into further actions.
From the tool's definition LLM-powered tool selection: sends your task description + a compact tool catalog to a fast model (Gemini 3 Flash, GPT-5-mini, or Claude Haiku 4.5) to pick the best 5-10 tools
Attacks that exploit this kind of access
The rule that runs smart_select_tools 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 smart_select_tools, this is the rule to start with:
smart_select_tools 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 smart_select_tools call is checked against it from then on.
Questions about smart_select_tools
LLM-powered tool selection: sends your task description + a compact tool catalog to a fast model (Gemini 3 Flash, GPT-5-mini, or Claude Haiku 4.5) to pick the best 5-10 tools. Much more accurate than keyword search for ambiguous queries like. 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 smart_select_tools: 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.
smart_select_tools 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 smart_select_tools 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 smart_select_tools. 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.
smart_select_tools 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