log_tool_call

Log an MCP tool call for profiling. Called automatically by the NodeBench gateway to track tool usage patterns, cost, and latency. Returns whether the call was redundant.

SERVERNodebench SOURCEnodebench-mcp
Low RISK CLASS
Category Read
Parameters 00 required
Recommended Allowedsee the rule below
Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-homenshum-nodebench/log-tool-call.md

What log_tool_call does on Nodebench

AI agents call log_tool_call 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 log_tool_call is rated Low

The tool is a logging and telemetry mechanism that captures call patterns and performance metrics. It has no side effects on user data or system state beyond writing immutable logs. The return value indicates redundancy detection, which is information-retrieval based.

From the tool's definition Logs tool calls for profiling, tracking usage patterns, cost, and latency; returns whether the call was redundant. This is purely observational—it reads/records metadata about tool calls without modifying data, executing code, or causing destructive effects.

Questions about log_tool_call

What does the log_tool_call tool do? +

Log an MCP tool call for profiling. Called automatically by the NodeBench gateway to track tool usage patterns, cost, and latency. Returns whether the call was redundant. It is categorised as a Read tool in the Nodebench MCP Server, which means it retrieves data without modifying state.

How do I enforce a policy on log_tool_call? +

Register the Nodebench MCP server in PolicyLayer and add a rule for log_tool_call: 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.

What risk level is log_tool_call? +

log_tool_call is a Read tool with low risk. Read-only tools are generally safe to allow by default.

Can I rate-limit log_tool_call? +

Yes. Add a rate_limit block to the log_tool_call 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.

How do I block log_tool_call completely? +

Set action: deny in the PolicyLayer policy for log_tool_call. 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.

What MCP server provides log_tool_call? +

log_tool_call 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

// THE MCP REGISTRY

PolicyLayer tracks 44,603 MCP servers and 515,000+ tools.

Every server has a live record: who publishes it, whether it answers without auth, its risk grade, every tool classified, the recommended policy. This page is one line of Nodebench's. Pull the full record:

Teams ship this data inside their own products. See what a licence covers →

// GET IN TOUCH

Have a question or want to learn more? Send us a message.

Message sent.

We'll get back to you soon.