lever_advanced_search
AI agents call lever_advanced_search to retrieve information from Lever ATS MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite the empty description, context from sibling tools and the 'advanced_search' naming strongly indicates this retrieves candidate or pipeline data without modifying it. The Lever ATS system manages hiring workflows, and search/find operations are typically read-only queries.
From the tool's definition Tool name 'lever_advanced_search' suggests querying candidate data; sibling tools like 'lever_find_candidate_in_posting', 'lever_find_candidates_for_role', and 'lever_get_candidate' are clearly Read operations for retrieving hiring pipeline information.
Attacks that exploit this kind of access
lever_advanced_search. It is categorised as a Read tool in the Lever ATS MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Lever ATS MCP Server MCP server in PolicyLayer and add a rule for lever_advanced_search: 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 Lever ATS MCP Server. Nothing to install.
lever_advanced_search 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 lever_advanced_search 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 lever_advanced_search. 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.
lever_advanced_search is provided by the Lever ATS MCP Server MCP server (the-sid-dani/lever-mcp-integration). 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 →