search_candidates
AI agents call search_candidates to retrieve information from Recruitee MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Despite empty description, the tool name and context of sibling read-only tools strongly suggest this searches/queries candidate records without modifying data. No evidence of write, delete, execute, or financial operations. The recruitment domain and LLM evaluation focus indicate passive data retrieval.
From the tool's definition Tool name 'search_candidates' and sibling tools (get_candidate_profile, get_candidates_from_pipeline, list_jobs) all indicate retrieval operations.
Attacks that exploit this kind of access
search_candidates. It is categorised as a Read tool in the Recruitee MCP Server MCP Server, which means it retrieves data without modifying state.
Register the Recruitee MCP Server MCP server in PolicyLayer and add a rule for search_candidates: 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 Recruitee MCP Server. Nothing to install.
search_candidates 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_candidates 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_candidates. 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_candidates is provided by the Recruitee MCP Server MCP server (pepuscz/recruitee-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 →