QueryKnowledgeBases
AI agents call QueryKnowledgeBases to retrieve information from Awslabs Valkey without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Based on the tool name, this appears to be a query/retrieval operation against knowledge bases, which is a Read operation. However, confidence is reduced to 0.6 because the description is absent, leaving some uncertainty about whether the tool might have side effects (e.g., logging queries, modifying access records) or if it executes arbitrary queries.
From the tool's definition Tool name 'QueryKnowledgeBases' indicates data retrieval operation. The description is empty, limiting certainty about actual behavior.
Attacks that exploit this kind of access
QueryKnowledgeBases. It is categorised as a Read tool in the Awslabs Valkey MCP Server, which means it retrieves data without modifying state.
Register the Awslabs Valkey MCP server in PolicyLayer and add a rule for QueryKnowledgeBases: 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 Awslabs Valkey. Nothing to install.
QueryKnowledgeBases 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 QueryKnowledgeBases 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 QueryKnowledgeBases. 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.
QueryKnowledgeBases is provided by the Awslabs Valkey MCP server (awslabs.valkey-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.