Skip to main content
Book a demo

Connect Paper to Claude Code

Give Claude Code governed access to Paper’s 19 tools through Runlayer, with identity, policy, scanning, and audit on every call.

Book a demo Claude Code setup guide

Set up

Add Paper to Claude Code in four steps

Admins approve the server once. Everyone in Claude Code then gets it through the same governed connection.

  1. 1

    Approve Paper in Runlayer

    Add Paper from the catalog and choose who can use it and which of its tools are allowed.

  2. 2

    Connect Claude Code to Runlayer

    Install the Runlayer CLI so Claude Code can reach Paper, which runs on the user’s machine. Auto Sync can then write Paper into Claude Code on macOS, Windows, and Linux.

    Claude Code setup guide
  3. 3

    Sign in to Paper

    Sign in the way Paper requires. Runlayer holds the credentials so they stay out of the client’s configuration.

  4. 4

    Use Paper from Claude Code

    Paper’s approved tools appear in Claude Code. Every call is checked against policy and recorded.

Tools

19 Paper tools in Claude Code

Runlayer policy decides which of these Claude Code users can call.

  • Get basic info

    Get essential context about the current design: file name, page name, node count, list of artboards with their dimensions, and a list of font families used in the document.

  • Get selection

    Get detailed information about the currently selected nodes, including IDs, names, component types, size, and which artboard they belong to.

  • Get node info

    Get detailed information about a specific node by ID, including its size, visibility, lock state, parent, children IDs, and text content.

  • Get children

    Get the direct children of a node.

  • Get screenshot

    Capture a screenshot of a specific node by ID.

  • Get jsx

    Get the JSX code representation of a node and its descendants.

  • Get tree summary

    Get a compact text summary of a node's subtree hierarchy showing component type, name, ID, and dimensions.

  • Get computed styles

    Get the computed CSS styles for one or more nodes.

See all 19 Paper tools

Control

What Runlayer can see and stop in Claude Code

Some controls apply to every client at the gateway. Others depend on what Claude Code exposes to Runlayer.

  • Gateway policy (available)

    Every Paper call from Claude Code passes through Runlayer, where your policies can allow, alert, mask, or block it.

  • Audit trail (available)

    Each call is recorded with the user, Claude Code as the client, the tool, and the policy and scanner decisions.

  • Client hooks (available)

    Capture supported prompts, reasoning, local and MCP tool calls, responses, and scanner decisions in real time.

  • Anthropic inference hooks (available)

    With Claude Enterprise, Anthropic sends each governed Claude Code prompt to Runlayer before inference, with nothing installed on devices (Anthropic beta).

  • OTLP telemetry (available)

    Claude Code can export OpenTelemetry logs to Runlayer for observe-only session reconstruction.

  • Stop a call before it runs (available)

    Runlayer can deny a tool call before Claude Code runs it.

  • Block output after it runs (available)

    Runlayer can block a tool’s output before Claude Code’s model sees it.

  • Redact output in place (available)

    Runlayer can mask sensitive parts of a tool’s output in Claude Code and pass the rest through.

In Claude Code

  • When a tool fails, Runlayer records the error but cannot hide it.

Frequently asked questions

Connect more

Find another combination