orion_query_entities
AI agents call orion_query_entities to retrieve information from Fiware Orion without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
Query operations on a context broker retrieve or search for entities without modifying, deleting, or executing external operations. Despite missing description (lowering confidence slightly), the naming convention and context of sibling Read tools (get, list) indicate this is a data retrieval operation with no side effects. Severity is low as the blast radius of misuse would be limited to information disclosure.
From the tool's definition Tool name 'orion_query_entities' suggests data retrieval (query) from FIWARE Orion Context Broker for entity information.
Attacks that exploit this kind of access
orion_query_entities. It is categorised as a Read tool in the Fiware Orion MCP Server, which means it retrieves data without modifying state.
Register the Fiware Orion MCP server in PolicyLayer and add a rule for orion_query_entities: 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 Fiware Orion. Nothing to install.
orion_query_entities 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 orion_query_entities 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 orion_query_entities. 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.
orion_query_entities is provided by the Fiware Orion MCP server (k2iser/fiware-orion-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 →