search_questions
AI agents call search_questions to retrieve information from SearchCAIE MCP Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool retrieves educational past-paper questions from a CAIE database with filtering capabilities. It has no capability to modify, delete, or execute code. The operation is read-only with no side effects beyond returning filtered data. The educational context and sibling naming conventions confirm this is a retrieval tool.
From the tool's definition Tool name 'search_questions' combined with server description indicating it 'retrieves CAIE past-paper questions with filters' and sibling tools like 'get_questions' and 'get_stats' that clearly retrieve data.
Attacks that exploit this kind of access
search_questions. It is categorised as a Read tool in the SearchCAIE MCP Server MCP Server, which means it retrieves data without modifying state.
Register the SearchCAIE MCP Server MCP server in PolicyLayer and add a rule for search_questions: 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 SearchCAIE MCP Server. Nothing to install.
search_questions 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_questions 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_questions. 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_questions is provided by the SearchCAIE MCP Server MCP server (pixel2075/searchcaie-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 →