create_entity · Lightrag MCP: Risk & Policy

WHAT IT DOES

What create_entity does on Lightrag

AI agents use create_entity 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.

WHY IT NEEDS A POLICY

Why create_entity needs a policy

The tool creates new entities in a knowledge graph, which is a data modification operation. It falls under Write rather than Execute because it performs a direct data creation action without executing arbitrary code or shell commands. It is reversible since the sibling delete_entity tool can remove created entities.

From the tool's definition Tool name 'create_entity' and description 'Create a new entity in the knowledge graph' indicate the tool creates new data in the graph. This is a write operation that modifies state but is reversible (entities can be deleted via delete_entity).

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

create_entity Rate-limited

create_entity stays usable, but capped — an agent stuck in a loop can't make hundreds of changes a minute. Everything else on the server is denied unless you say otherwise.

View as policy code

policy.json

{
  "version": "1",
  "default": "deny",
  "tools": {
    "create_entity": {
      "limits": [
        {
          "counter": "create_entity_rate",
          "window": "minute",
          "max": 30,
          "scope": "grant"
        }
      ]
    }
  }
}

LIMIT THIS TOOL →

Instant setup, no code required.

PolicyLayer is an MCP gateway: every tool call is checked against your rule before it reaches Lightrag, so you can run agents against it safely.

FAQ

Questions about create_entity

What does the create_entity tool do? +

Create a new entity 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.

How do I enforce a policy on create_entity? +

Register the Lightrag MCP server in PolicyLayer and add a rule for create_entity: 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.

What risk level is create_entity? +

create_entity is a Write tool with medium risk. Write tools should be rate-limited to prevent accidental bulk modifications.

Can I rate-limit create_entity? +

Yes. Add a rate_limit block to the create_entity 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.

How do I block create_entity completely? +

Set action: deny in the PolicyLayer policy for create_entity. 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.

What MCP server provides create_entity? +

create_entity 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.