AI agents call get_hints to retrieve information from Nikhilnt without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves and analyzes existing token usage data to generate optimization recommendations. It has no side effects—it does not create, modify, delete, or execute operations. The output is informational (hints and savings estimates).
From the tool's definition Tool performs analysis and returns ranked hints with estimated savings; uses verbs 'Analyse' and 'return' indicating data retrieval and computation without modifying state.
Attacks that exploit this kind of access
Analyse your token usage and return ranked optimisation hints with estimated monthly savings. It is categorised as a Read tool in the Nikhilnt MCP Server, which means it retrieves data without modifying state.
Register the Nikhilnt MCP server in PolicyLayer and add a rule for get_hints: 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 Nikhilnt. Nothing to install.
get_hints 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 get_hints 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 get_hints. 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.
get_hints is provided by the Nikhilnt MCP server (nikhilnt1234/tokenburnrate). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
get_hints is one line of Nikhilnt's registry record.
The record carries the whole server: verified identity, auth posture, risk grade, every tool classified, recommended policy — re-checked continuously.
Teams ship this data inside their own products. See what a licence covers →