npm package discovery and stats viewer.

Discover Tips

  • General search

    [free text search, go nuts!]

  • Package details

    pkg:[package-name]

  • User packages

    @[username]

Sponsor

Optimize Toolset

I’ve always been into building performant and accessible sites, but lately I’ve been taking it extremely seriously. So much so that I’ve been building a tool to help me optimize and monitor the sites that I build to make sure that I’m making an attempt to offer the best experience to those who visit them. If you’re into performant, accessible and SEO friendly sites, you might like it too! You can check it out at Optimize Toolset.

About

Hi, 👋, I’m Ryan Hefner  and I built this site for me, and you! The goal of this site was to provide an easy way for me to check the stats on my npm packages, both for prioritizing issues and updates, and to give me a little kick in the pants to keep up on stuff.

As I was building it, I realized that I was actually using the tool to build the tool, and figured I might as well put this out there and hopefully others will find it to be a fast and useful way to search and browse npm packages as I have.

If you’re interested in other things I’m working on, follow me on Twitter or check out the open source projects I’ve been publishing on GitHub.

I am also working on a Twitter bot for this site to tweet the most popular, newest, random packages from npm. Please follow that account now and it will start sending out packages soon–ish.

Open Software & Tools

This site wouldn’t be possible without the immense generosity and tireless efforts from the people who make contributions to the world and share their work via open source initiatives. Thank you 🙏

© 2026 – Pkg Stats / Ryan Hefner

smallright

v0.4.1

Published

AI-friendly browser automation MCP server that reduces token consumption by zone-based partial DOM retrieval

Readme

smallright

AI-friendly browser automation MCP server that reduces token consumption by zone-based partial DOM retrieval.

Features

  • Zone-based DOM retrieval — split pages into zones (header/main/sidebar/footer) and fetch only what you need
  • Text/label element resolution — interact with elements by text, label, or role; no CSS selectors or ref IDs needed
  • Batch execution — run multiple actions in one call to reduce MCP round-trips
  • Site profiles — persist zone definitions per domain so detection only happens once

Installation

npm install
npm run build
npx playwright install chromium

MCP Configuration

Add the following to your .mcp.json:

{
  "mcpServers": {
    "smallright": {
      "type": "stdio",
      "command": "node",
      "args": ["/path/to/smallright/dist/index.js"]
    }
  }
}

Quick Start

# 1. Navigate to a page
navigate(url: "https://example.com/login")

# 2. Read the page to see available elements
read_page()

# 3. Interact using text/label — no selectors needed
fill(label: "Email", value: "[email protected]")
fill(label: "Password", value: "secret")
click(text: "Login")

# 4. Read only the relevant zone after the action
read_page(zone: "main")

Tools

High-level (9 tools)

| Tool | Description | |---|---| | navigate | Navigate to a URL and return the list of interactive elements | | read_page | Get interactive elements and content of the current page; supports zone filtering | | click | Click an element identified by text; returns StateDiff of changed zones | | fill | Fill a field identified by label; returns StateDiff of changed zones | | fill_form | Fill multiple fields at once using a label→value map | | select_option | Select a dropdown option identified by label | | read_table | Return the first matching table as a JSON array | | run_batch | Execute multiple steps in one call and return the final StateDiff | | screenshot | Capture the current page or a specific zone as a Base64 image |

Mid-level (5 tools)

| Tool | Description | |---|---| | setup_page | Auto-detect zones on the current page | | define_zones | Manually define zones for the current session | | save_profile | Save the current zone definitions as a site profile for a domain | | list_profiles | List all saved site profiles | | delete_profile | Delete the site profile for a domain |

Low-level (2 tools)

| Tool | Description | |---|---| | get_state | Fallback tool to retrieve raw page state; action mode or visual (full DOM) mode | | evaluate | Execute arbitrary JavaScript in the browser and return the result as JSON |

Environment Variables

| Variable | Default | Description | |---|---|---| | SMALLRIGHT_HEADLESS | true | Set to false to run the browser in headed (visible) mode |

Security

  • evaluate tool: Executes arbitrary JavaScript in the browser. Only pass trusted, validated input. Never forward unsanitized user input to this tool.
  • data-smallright-ref attributes: smallright adds temporary data-smallright-ref attributes to DOM elements during element scanning for internal tracking. These are cleaned up after each operation but may be visible in live DOM inspection.

License

MIT