sync_resume · Narrarium MCP: Risk & Policy

WHAT IT DOES

What sync_resume does on Narrarium

AI agents use sync_resume 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 sync_resume needs a policy

The tool regenerates/updates summary data (resumes) for chapters or the whole book based on the current repository state. This is a write/update operation that modifies stored resume data, but it is reversible and does not delete content or execute arbitrary code. It does not move money, destroy data, or run external commands.

From the tool's definition Refresh a chapter resume or the total book resume from the current repository state

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

sync_resume Rate-limited

sync_resume 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": {
    "sync_resume": {
      "limits": [
        {
          "counter": "sync_resume_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 sync_resume

What does the sync_resume tool do? +

Refresh a chapter resume or the total book resume from the current repository state without calling another model. 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 sync_resume? +

Register the Narrarium MCP server in PolicyLayer and add a rule for sync_resume: 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 sync_resume? +

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

Can I rate-limit sync_resume? +

Yes. Add a rate_limit block to the sync_resume 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 sync_resume completely? +

Set action: deny in the PolicyLayer policy for sync_resume. 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 sync_resume? +

sync_resume 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.