AI agents call get_knowledge_graph 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 tool queries and retrieves data from a knowledge graph without any side effects. It reads an existing subgraph structure without creating, modifying, or deleting any entities or relations. The operation is a pure read with no ability to cause unintended consequences or damage.
From the tool's definition Tool name is 'get_knowledge_graph' and description states 'Retrieve a connected subgraph of nodes' — uses retrieval verb 'Retrieve' with no modification or deletion of data.
Attacks that exploit this kind of access
Retrieve a connected subgraph of nodes. 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 get_knowledge_graph: 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.
get_knowledge_graph 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 get_knowledge_graph 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 get_knowledge_graph. 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.
get_knowledge_graph 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 →