Skip to main content
Paperzilla is designed for both human reading and programmatic use. This guide focuses on Paperzilla as a data layer for agents.

Available interfaces

Use these depending on your workflow:
  • CLI (pz) for shell/script execution
  • MCP (/api/mcp) for LLM tool-calling workflows
  • RSS/Atom for polling in feed infrastructure
See CLI guide, MCP integration, Codex guide, Claude guide, and RSS/Atom guide. For a walkthrough, automate a CLI feed export or connect a custom agent via MCP.
  1. Create and tune projects in the app.
  2. Authenticate CLI with pz login.
  3. Use pz project list --json to get the project ID you need from structured output.
  4. Use pz feed <project-id> --json for browse-style automation, or pz feed search --project-id <id> --query <q> --json for text search across the full feed.
  5. Use --must-read, --since, or --limit with pz feed. To filter search results by your feedback, use pz feed search --feedback-filter.

OpenClaw skill

The Paperzilla CLI is published as an OpenClaw skill on ClawHub. Install it with openclaw skills install paperzilla to let OpenClaw use pz commands directly. If you already use the separate ClawHub CLI, clawhub install paperzilla also works. See Use the Paperzilla CLI with OpenClaw for the full setup flow.

Codex

Start with the Paperzilla plugin in Codex. Install the plugin and connect your account to give Codex access to Paperzilla’s research tools.
For a managed configuration, see manual MCP setup in Codex. Use pz directly when Codex works in a shell or repo. A Codex skill for Paperzilla can document how to check the setup, find the relevant docs, and use the tools in order.

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

MCP tools

Use the OAuth MCP guide and tool reference. Public digests and catalog papers work with any authenticated account. Reading Markdown and requesting generation are separate tools. Project-specific tools require an owned project.

Example workflows

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.