Search optimized for question-answer pairs
AI agents call search_qa to retrieve information from RAG-MCP Knowledge Base Server without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This tool performs semantic search to retrieve question-answer pairs from a knowledge base. It retrieves data without creating, modifying, deleting, or executing external operations. The search functionality is read-only with no side effects on the underlying data or systems.
From the tool's definition Tool name is 'search_qa' and description states it is 'Search optimized for question-answer pairs'. The server enables 'semantic search across text documents' with no modification or deletion capabilities mentioned. This is a retrieval operation.
Attacks that exploit this kind of access
Search optimized for question-answer pairs. It is categorised as a Read tool in the RAG-MCP Knowledge Base Server MCP Server, which means it retrieves data without modifying state.
Register the RAG-MCP Knowledge Base Server MCP server in PolicyLayer and add a rule for search_qa: 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 RAG-MCP Knowledge Base Server. Nothing to install.
search_qa 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_qa 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_qa. 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_qa is provided by the RAG-MCP Knowledge Base Server MCP server (luxter77/mcp-kbdb). 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 →