Skip to main content
AI agents: This page is available as markdown. See also the docs index and full docs.
Paperzilla is designed for both human reading and programmatic use. This guide focuses on Paperzilla as a data layer for agents.

​
Available today: CLI data access

Use the Paperzilla CLI (pz) as the primary interface for agents and scripts. With CLI you can:
  • List projects
  • Fetch project feed items
  • Filter for Must Read
  • Request JSON output for automation
  • Get RSS/Atom feed URLs
See CLI guide for commands.
  1. Create and tune projects in the app.
  2. Authenticate CLI with pz login.
  3. Use pz feed <project-id> --json in your automation.
  4. Add filters (--must-read, --since, --limit) based on your workflow.

​
Data surfaces you can combine

  • App feed for visual review
  • CLI for structured automation
  • RSS/Atom for polling in feed infrastructure
  • Email digests for human review cadence

​
Coming soon: MCP integration

A Paperzilla MCP integration is planned so LLM tools can call Paperzilla capabilities directly. Read status and scope: MCP integration (coming soon).

​
Why this matters

If your workflow depends on “fresh papers + relevance filtering + automation,” treat Paperzilla projects as the persistent source and let agents consume that data layer.