AI agents call get_company_stats to retrieve information from H1b without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs a lookup/query operation on publicly available H1B visa data. It returns aggregated statistics (approval rates, roles, wages, locations) without any ability to create, modify, delete, or execute code. The data queried is explicitly stated as coming from public Department of Labor records, confirming a read-only nature. No side effects occur from calling this tool.
From the tool's definition Tool 'get_company_stats' retrieves 'detailed H1B stats for a company: approval rate, top roles, avg wage, and states' — all read operations that query public Department of Labor records with no modification, deletion, or execution capability.
Attacks that exploit this kind of access
Get detailed H1B stats for a company: approval rate, top roles, avg wage, and states. It is categorised as a Read tool in the H1b MCP Server, which means it retrieves data without modifying state.
Register the H1b MCP server in PolicyLayer and add a rule for get_company_stats: 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 H1b. Nothing to install.
get_company_stats 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_company_stats 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_company_stats. 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_company_stats is provided by the H1b MCP server (yoginoit39/jobsearch-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 →