Query device vector store
AI agents call iot_store_query to retrieve information from Claude Flow without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool performs a query operation on a vector store, which is fundamentally a read-only data retrieval action. Vector store queries retrieve or search existing data without creating, modifying, deleting, or executing external operations. The 'query' verb combined with 'device vector store' context confirms this is a Read category tool with minimal risk.
From the tool's definition Tool name 'iot_store_query' and description 'Query device vector store' indicate a retrieval/query operation with no modification or side effects.
Attacks that exploit this kind of access
Query device vector store. It is categorised as a Read tool in the Claude Flow MCP Server, which means it retrieves data without modifying state.
Register the Claude Flow MCP server in PolicyLayer and add a rule for iot_store_query: 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 Claude Flow. Nothing to install.
iot_store_query 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 iot_store_query 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 iot_store_query. 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.
iot_store_query is provided by the Claude Flow MCP server (claude-flow). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.