sniff_record_human_review

Record a human sniff-check for a subtask or merge output.

SERVERNodebench SOURCEnodebench-mcp

Medium RISK CLASS

Category Write

Parameters 00 required

Recommended Rate-limitedsee the rule below

Registry record Grade F, identity unverified Pull the record →

This record as markdown: /tools/io-github-homenshum-nodebench/sniff-record-human-review.md

WHAT IT DOES

What sniff_record_human_review does on Nodebench

AI agents use sniff_record_human_review to create or update resources in Nodebench, usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Nodebench environment.

RISK

Why sniff_record_human_review is rated Medium

The tool records (writes) the result of a human review check. This is a data creation/modification action with no indication of code execution, deletion, or financial impact. Severity is low as it only logs review metadata.

From the tool's definition 'Record a human sniff-check' — explicitly stores/writes a review record for a subtask or merge output

Attacks that exploit this kind of access

RECOMMENDED RULE

The rule that runs sniff_record_human_review 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 sniff_record_human_review, this is the rule to start with:

sniff_record_human_review Rate-limited

sniff_record_human_review stays usable, but capped: an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "sniff_record_human_review": {
      "limits": [
        {
          "counter": "sniff_record_human_review_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL → Instant setup, no code required.

The button opens the PolicyLayer dashboard: create your workspace, connect Nodebench, apply this rule, and every sniff_record_human_review call is checked against it from then on.

FAQ

Questions about sniff_record_human_review

What does the sniff_record_human_review tool do? +

Record a human sniff-check for a subtask or merge output. It is categorised as a Write tool in the Nodebench MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on sniff_record_human_review? +

Register the Nodebench MCP server in PolicyLayer and add a rule for sniff_record_human_review: 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 sniff_record_human_review? +

sniff_record_human_review is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit sniff_record_human_review? +

Yes. Add a rate_limit block to the sniff_record_human_review 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 sniff_record_human_review completely? +

Set action: deny in the PolicyLayer policy for sniff_record_human_review. 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 sniff_record_human_review? +

sniff_record_human_review 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.

KEEP EXPLORING

More on Nodebench, and thousands of servers like it.

This server

All 824 Nodebench tools →

Across the catalogue

aroflo_create_or_update_record on AroFlo MCP →team_manager_record_checkpoint on Team Manager MCP → The MCP Attack Database →

Guides

Govern customer-ops agents →Argument validation →Scoped token →