mark_almost_finished · Mcp Elevenreader MCP: Risk & Policy

WHAT IT DOES

What mark_almost_finished does on Mcp Elevenreader

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

WHY IT NEEDS A POLICY

Why mark_almost_finished needs a policy

The tool updates progress tracking data for documents, changing their completion status. This is a state modification (Write category) rather than destructive deletion, and affects only metadata related to reading progress, not core data deletion. The operation is reversible—a user could manually adjust progress again.

From the tool's definition Tool description states it will 'mark them as finished by setting offset to char_count' — this modifies the progress state of books in the user's library, which is a reversible write operation.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

mark_almost_finished Rate-limited

mark_almost_finished 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": {
    "mark_almost_finished": {
      "limits": [
        {
          "counter": "mark_almost_finished_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 Mcp Elevenreader, so you can run agents against it safely.

FAQ

Questions about mark_almost_finished

What does the mark_almost_finished tool do? +

Find books at 97-99% progress (not yet marked completed) and mark them as finished by setting offset to char_count. It is categorised as a Write tool in the Mcp Elevenreader MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on mark_almost_finished? +

Register the Mcp Elevenreader MCP server in PolicyLayer and add a rule for mark_almost_finished: 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 Mcp Elevenreader. Nothing to install.

What risk level is mark_almost_finished? +

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

Can I rate-limit mark_almost_finished? +

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

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

mark_almost_finished is provided by the Mcp Elevenreader MCP server (mit9/mcp-elevenreader). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.