AI agents call check_entity_exists to retrieve information from Lightrag without modifying anything — typically the context-gathering step in research, monitoring, and reporting workflows, before the agent takes action elsewhere.
This is a read-only operation that queries the knowledge graph to verify if an entity exists. It has no side effects, does not modify data, and presents minimal risk if misused by an AI agent. The tool simply returns a boolean or status about existing data.
From the tool's definition Tool name and description both indicate a query operation: 'check if an entity...exists'. No modification, deletion, or execution of code is performed. The operation only retrieves existence status.
Attacks that exploit this kind of access
Check if an entity with the given name exists in the knowledge graph. It is categorised as a Read tool in the Lightrag MCP Server, which means it retrieves data without modifying state.
Register the Lightrag MCP server in PolicyLayer and add a rule for check_entity_exists: 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 Lightrag. Nothing to install.
check_entity_exists 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 check_entity_exists 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 check_entity_exists. 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.
check_entity_exists is provided by the Lightrag MCP server (lightrag-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 →