update_entity · Narrarium MCP: Risk & Policy

WHAT IT DOES

What update_entity does on Narrarium

AI agents use update_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 update_entity needs a policy

This tool modifies (writes to) existing entity data within the Narrarium book repository system. It is reversible—modifications can be undone by applying different patches or overwriting with previous content. It does not delete, destroy, or move entities (that's handled by rename_entity).

From the tool's definition Tool description states it 'Update[s] an existing entity file by patching frontmatter and optionally replacing or appending markdown body content.' The verbs 'patching,' 'replacing,' and 'appending' indicate modification of existing data.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

update_entity Rate-limited

update_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": {
    "update_entity": {
      "limits": [
        {
          "counter": "update_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 update_entity

What does the update_entity tool do? +

Update an existing entity file by patching frontmatter and optionally replacing or appending markdown body content. Use rename_entity when the slug, id, or asset folder must move. 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 update_entity? +

Register the Narrarium MCP server in PolicyLayer and add a rule for update_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 update_entity? +

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

Can I rate-limit update_entity? +

Yes. Add a rate_limit block to the update_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 update_entity completely? +

Set action: deny in the PolicyLayer policy for update_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 update_entity? +

update_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.