AI agents call search_employers to retrieve information from Handshake without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool searches or queries employer data within the Handshake job platform. Sibling tools like 'get_employer_profile', 'search_jobs', and 'search_events' confirm this server's pattern of providing read-only lookup and query operations. No side effects, modifications, or destructive actions are evident.
From the tool's definition Tool name 'search_employers' and server description indicating ability to 'browse employers' and 'pull employer profiles' indicates query/search functionality for browsing data without modification.
Attacks that exploit this kind of access
search_employers. It is categorised as a Read tool in the Handshake MCP Server, which means it retrieves data without modifying state.
Register the Handshake MCP server in PolicyLayer and add a rule for search_employers: 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 Handshake. Nothing to install.
search_employers 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_employers 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_employers. 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_employers is provided by the Handshake MCP server (sudhxnva/handshake-mcp-server). 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 →