process_kindle_export · Kindle MCP: Risk & Policy

WHAT IT DOES

What process_kindle_export does on Kindle

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

WHY IT NEEDS A POLICY

Why process_kindle_export needs a policy

This tool processes Kindle exports and coordinates writing summarized data to Notion. While it parses local files (Read-like activity), its primary documented purpose is to prepare data for persistent storage via push_to_notion. The Write category applies because the tool orchestrates creation of new Notion pages and structured records.

From the tool's definition 'push_to_notion' indicates the tool creates or modifies data in Notion ('saves to Notion'). 'generates...summaries saved to Notion' and 'immediately call push_to_notion for each book' confirm data creation/modification.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

process_kindle_export Rate-limited

process_kindle_export 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": {
    "process_kindle_export": {
      "limits": [
        {
          "counter": "process_kindle_export_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 Kindle, so you can run agents against it safely.

FAQ

Questions about process_kindle_export

What does the process_kindle_export tool do? +

PRIMARY TOOL. Given the raw content of a Kindle HTML export or My Clippings.txt file, parses all highlights and returns prompt packages plus explicit instructions. After calling this tool, you MUST follow the returned instructions exactly: generate each summary internally then immediately call push_to_notion for each book. Do not display summaries in chat — only report the Notion page URLs. It is categorised as a Write tool in the Kindle MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on process_kindle_export? +

Register the Kindle MCP server in PolicyLayer and add a rule for process_kindle_export: 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 Kindle. Nothing to install.

What risk level is process_kindle_export? +

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

Can I rate-limit process_kindle_export? +

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

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

process_kindle_export is provided by the Kindle MCP server (silcfcr/kindle-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.