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

mu-webfetch

v0.38.2

Published

Webfetch tool for mu — fetches a URL and returns it as markdown by default.

Readme

mu-webfetch

Plugin that adds a webfetch tool to mu. Fetches the contents of a URL and returns it as markdown — adapted from opencode's webfetch tool.

Originally ported from the webfetch pi-coding-agent extension.

Tool

  • webfetch — fetch a URL.
    • url (string, required) — fully-formed http(s) URL.
    • timeout (number, optional) — seconds, capped at 120.
    • Returns the response body. HTML responses are converted to markdown; other text content types are returned as-is. Errors come back as a plain string prefixed with Error:.

Image responses

For image/* responses (excluding image/svg+xml and image/vnd.microsoft.icon) the tool returns a single string of the form:

[image: <mime>, <byteLength> bytes from <url>]
data:<mime>;base64,<base64-payload>

Use sparingly — base64 inlining can blow the model's context window.

Limits

  • Size cap: responses larger than 5 MB are rejected (checked against both the content-length header and the actual body length).
  • Timeout: default 30 s, max 120 s. Configurable via the timeout parameter.
  • Redirects: at most 5 hops; each target is re-validated against the SSRF blocklist.
  • Cloudflare retry: a 403 cf-mitigated: challenge response triggers one retry with User-Agent: mu (the first attempt uses a regular browser UA).

Enable it

Add the plugin to your mu config (~/.config/mu/config.json):

{
  "plugins": ["mu-webfetch"]
}

If you publish or install via npm, use "npm:mu-webfetch" instead — the loader will auto-install the package on first run.

Permissioning per agent

Permissions are authored in an agent file's tools: frontmatter map, keyed by tool name (globs supported), with a per-tool decision:

tools:
  webfetch: allow # or `ask` / `deny`

webfetch can only be granted at the whole-tool level — there is no argument-level (per-URL) scoping. Per-argument grants exist only for skill (by skill name) and bash (by command).

Implementation notes

  • HTML→markdown conversion uses turndown with script, style, meta, link stripped.
  • The first request uses a Chrome-like User-Agent plus a quality-weighted Accept header that prefers markdown when servers offer it.