AI agents call get_summary 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 displays historical token usage and cost metrics across a specified time period. It is a read-only operation with no side effects—it queries existing data and presents a summary. No data is created, modified, deleted, or financial transactions are executed. The low severity reflects minimal risk if misused by an AI agent, as it only exposes historical billing/usage information.
From the tool's definition Tool name 'get_summary' and description 'Get token usage and cost summary' indicate a retrieval/query operation that returns aggregated data without modifying, deleting, or executing external operations.
Attacks that exploit this kind of access
Get token usage and cost summary for a time period. 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_summary: 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_summary 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_summary 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_summary. 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_summary 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.
Every MCP server has a record like this.
Type a name, get the same breakdown: verified identity, auth posture, risk grade, capabilities, recommended policy.
Teams ship this data inside their own products. See what a licence covers →