AI agents call entity_query to retrieve information from Jarvis Orb without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
The tool queries existing entities from the persistent memory system, allowing retrieval by filtering on type and name. This is a non-destructive read operation with no capability to modify, execute, or delete data. The blast radius of misuse is minimal—an agent can only retrieve information already stored in the system.
From the tool's definition Tool name 'entity_query' combined with description 'Query entities by type and/or name' indicates a retrieval operation with no modification or side effects.
Documented attack patterns abuse exactly the kind of access entity_query gives an agent:
PolicyLayer is an MCP gateway — it sits between your AI agents and Jarvis Orb, and nothing reaches the server without passing your rules. This is the rule we recommend for entity_query:
{
"version": "1",
"default": "deny",
"tools": {
"entity_query": {}
}
}entity_query is read-only, so it stays allowed — but everything else on the server is denied unless you say otherwise.
Free to start. No card required.
Query entities by type and/or name. It is categorised as a Read tool in the Jarvis Orb MCP Server, which means it retrieves data without modifying state.
Register the Jarvis Orb MCP server in PolicyLayer and add a rule for entity_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 Jarvis Orb. Nothing to install.
entity_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 entity_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 entity_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.
entity_query is provided by the Jarvis Orb MCP server (thestack-ai/jarvis-orb). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.
Start from Jarvis Orb, add the rest of your stack, and see everything your agents can call. Then put policy on all of it.
Free to start. No card required.
7 Jarvis Orb tools catalogued and risk-classified — across an index of 43,000+ MCP servers.