Check your FreshFilings API key usage and remaining calls this month.
AI agents call check_usage to retrieve information from Freshfilings without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool retrieves usage metrics and quota information about the API key holder's account. It performs a query operation to read current usage data without modifying, executing commands, deleting data, or affecting financial state. The low severity reflects minimal blast radius if misused—the worst outcome would be unauthorized visibility into usage patterns, which is informational only.
From the tool's definition Tool description states: 'Check your FreshFilings API key usage and remaining calls this month.' This is a read-only query of usage statistics with no side effects.
Attacks that exploit this kind of access
Check your FreshFilings API key usage and remaining calls this month. It is categorised as a Read tool in the Freshfilings MCP Server, which means it retrieves data without modifying state.
Register the Freshfilings MCP server in PolicyLayer and add a rule for check_usage: 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 Freshfilings. Nothing to install.
check_usage 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 check_usage 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 check_usage. 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.
check_usage is provided by the Freshfilings MCP server (nrfischer10/freshfilings-mcp). 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 →