call_llm
Call an LLM model directly and get the response with metrics (tokens, latency). Uses available API keys: Gemini → OpenAI → Anthropic. Useful for eval-driven workflows, model comparison, structured analysis, and any task where the agent needs an LLM call as a step in its pipeline.
This record as markdown: /tools/io-github-homenshum-nodebench/call-llm.md
What call_llm does on Nodebench
AI agents invoke call_llm 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 call_llm is rated High
This tool triggers external API calls to LLM providers (Gemini, OpenAI, Anthropic), consuming API credits and executing potentially arbitrary prompts against those models. It is an Execute-category tool because it runs an external operation whose effects depend on the arguments passed.
From the tool's definition 'Call an LLM model directly and get the response' and 'any task where the agent needs an LLM call as a step in its pipeline'
Attacks that exploit this kind of access
The rule that runs call_llm 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 call_llm, this is the rule to start with:
call_llm 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 call_llm call is checked against it from then on.
Questions about call_llm
Call an LLM model directly and get the response with metrics (tokens, latency). Uses available API keys: Gemini → OpenAI → Anthropic. Useful for eval-driven workflows, model comparison, structured analysis, and any task where the agent needs an LLM call as a step in its pipeline. 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 call_llm: 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.
call_llm 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 call_llm 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 call_llm. 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.
call_llm 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