AI agents use create_relation to create or update resources in Lightrag — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Lightrag environment.
This tool creates new relationships in the knowledge graph, which is a reversible write operation. The severity is medium because while the action is reversible (relationships can be deleted), the knowledge graph is a critical data structure and malicious relationship creation could pollute or corrupt the graph with false connections, requiring cleanup efforts.
From the tool's definition Tool description states 'Create a new relationship between two entities in the knowledge graph', explicitly indicating creation of new data within the graph structure.
Attacks that exploit this kind of access
Create a new relationship between two entities in the knowledge graph. It is categorised as a Write tool in the Lightrag MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.
Register the Lightrag MCP server in PolicyLayer and add a rule for create_relation: 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.
create_relation is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.
Yes. Add a rate_limit block to the create_relation 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 create_relation. 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.
create_relation 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 →