generate_digest · Paper Distill MCP: Risk & Policy

WHAT IT DOES

What generate_digest does on Paper Distill MCP

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

WHY IT NEEDS A POLICY

Why generate_digest needs a policy

This tool creates or modifies data reversibly by generating output files in multiple formats. While it writes data to disk, these operations are not irreversible (files can be regenerated or deleted), and there is no destructive, financial, or arbitrary code execution involved. The output appears to be structured data exports supporting the paper curation workflow.

From the tool's definition Tool generates and writes multiple output files (pushes.jsonl, papers.jsonl, Astro site JSON, Obsidian notes). The verb 'generate' combined with explicit file creation across multiple formats indicates data creation/modification operations.

Attacks that exploit this kind of access

Recommended rule Ready

Verdict

generate_digest Rate-limited

generate_digest 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": {
    "generate_digest": {
      "limits": [
        {
          "counter": "generate_digest_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 Paper Distill MCP, so you can run agents against it safely.

FAQ

Questions about generate_digest

What does the generate_digest tool do? +

Generate all daily output files (pushes.jsonl, papers.jsonl, Astro site JSON, Obsidian notes). It is categorised as a Write tool in the Paper Distill MCP MCP Server, which means it can create or modify data. Consider rate limits to prevent runaway writes.

How do I enforce a policy on generate_digest? +

Register the Paper Distill MCP server in PolicyLayer and add a rule for generate_digest: 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 Paper Distill MCP. Nothing to install.

What risk level is generate_digest? +

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

Can I rate-limit generate_digest? +

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

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

generate_digest is provided by the Paper Distill MCP server (pypi:paper-distill-mcp). PolicyLayer sits as a proxy in front of this server to enforce policies before tool calls reach the server.