query_items
Read item data. action: all (list with optional filters), get (by name), multi (batch by names), search (fuzzy text), master_search (across items+things+rules), room_inventory, semantic_path, neighbors, schema.
This record as markdown: /tools/deswong-openhab-mcp/query-items.md
What query_items does on Openhab
AI agents call query_items to retrieve information from Openhab without modifying anything. It is typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Why query_items is rated Low
query_items performs only data retrieval and querying across items, things, and rules without any side effects. The tool cannot modify, delete, or execute state changes. While it provides broad visibility into the home automation system, the risk is limited to information disclosure, making it a Read classification with low severity.
From the tool's definition Tool description explicitly states 'Read item data' and lists query operations: 'list with optional filters', 'get (by name)', 'batch by names', 'search', 'master_search', 'room_inventory', 'semantic_path', 'neighbors', 'schema'.
Attacks that exploit this kind of access
The rule that runs query_items safely
PolicyLayer is an MCP gateway: it sits between your AI agents and Openhab, and checks every tool call against a rule you set before the call runs. Nothing changes on the server itself. For query_items, this is the rule to start with:
query_items is read-only, so it stays allowed. Everything else on the server is denied unless you say otherwise.
The button opens the PolicyLayer dashboard: create your workspace, connect Openhab, apply this rule, and every query_items call is checked against it from then on.
Questions about query_items
Read item data. action: all (list with optional filters), get (by name), multi (batch by names), search (fuzzy text), master_search (across items+things+rules), room_inventory, semantic_path, neighbors, schema. It is categorised as a Read tool in the Openhab MCP Server, which means it retrieves data without modifying state.
Register the Openhab MCP server in PolicyLayer and add a rule for query_items: 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 Openhab. Nothing to install.
query_items 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 query_items 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 query_items. 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.
query_items is provided by the Openhab MCP server (deswong/openhab-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
More on Openhab, and thousands of servers like it.
This server
Across the catalogue