rename_entity · Narrarium MCP: Risk & Policy

WHAT IT DOES

What rename_entity does on Narrarium

AI agents use rename_entity to create or update resources in Narrarium — usually the action step of a workflow, after the agent has gathered context. Every call changes real data in your Narrarium environment.

WHY IT NEEDS A POLICY

Why rename_entity needs a policy

rename_entity performs structured updates to entity metadata (slug, id) and file reorganization (moving markdown files and asset folders), but these changes are reversible and don't destroy data. This is a Write operation rather than Destructive because renaming is not irreversible; the entity and its assets continue to exist under a new identifier.

From the tool's definition Tool 'renames' an entity and 'updates its slug and id, moves its markdown file, and moves any matching asset folder' — these are reversible modifications to data structure and file organization within a book repository.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

rename_entity Rate-limited

rename_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": {
    "rename_entity": {
      "limits": [
        {
          "counter": "rename_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 Narrarium, so you can run agents against it safely.

FAQ

Questions about rename_entity

What does the rename_entity tool do? +

Rename an entity in a safe way: update its slug and id, move its markdown file, and move any matching asset folder if present. It is categorised as a Write tool in the Narrarium MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on rename_entity? +

Register the Narrarium MCP server in PolicyLayer and add a rule for rename_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 Narrarium. Nothing to install.

What risk level is rename_entity? +

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

Can I rate-limit rename_entity? +

Yes. Add a rate_limit block to the rename_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 rename_entity completely? +

Set action: deny in the PolicyLayer policy for rename_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 rename_entity? +

rename_entity is provided by the Narrarium MCP server (narrarium-mcp-server). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.