AI agents use update_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 or modifies data reversibly—it updates relations without deleting them permanently. The effect is limited to a specific relation and can theoretically be undone by updating again or reverting the change. This fits the Write category rather than Execute (no code execution or external operations) or Destructive (changes are reversible).
From the tool's definition Tool name is 'update_relation' and description states 'Update a relation', which modifies existing relation data in the LightRag knowledge graph.
Attacks that exploit this kind of access
Update a relation\. 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 update_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.
update_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 update_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 update_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.
update_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 →