AI agents call search_sponsors 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 retrieves and filters publicly available H1B sponsorship data from Department of Labor records without modifying, executing operations, or causing side effects. It is a search/query operation that returns filtered datasets based on user-provided parameters (job_title, state, city).
From the tool's definition Tool description states 'Find companies that sponsor H1Bs' with filtering capabilities. The server provides 'query' access to 'public Department of Labor records' with no mention of modification, deletion, or execution capabilities.
Attacks that exploit this kind of access
Find companies that sponsor H1Bs. Filter by job_title, state (2-letter), and/or city. 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 search_sponsors: 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.
search_sponsors 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 search_sponsors 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 search_sponsors. 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.
search_sponsors 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 →