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

@glbforge/mcp

v0.6.0

Published

GLBForge MCP server — 8 tools that let AI agents take 3D assets from generation to web-ready.

Readme

@glbforge/mcp

MCP server exposing the glbforge pipeline to AI agents (Claude Code, Cursor, ...).

claude mcp add glbforge -- npx -y @glbforge/mcp

Built for agents, not terminals:

  • Compact results. analyze_glb, optimize_glb, and ship_asset return the verdict, the numbers that drive decisions, the top three findings, nextActions (the tool calls that would fix the failures) and a drillDown pointer — as JSON text and as structuredContent.
  • Drill-down on demand. inspect_report returns any full section — findings (with fix suggestions, filterable by rule prefix / severity), textures, materials, topology, geometry, scene, or all. Analysis is deterministic and fast, so nothing is cached server-side.
  • See what you made. Every tool that reads or writes a GLB also returns a rendered PNG (preview: thumbnail | turntable | none) from the deterministic software rasterizer — no GPU, same file = same pixels. render_preview does it standalone (2x2 turntable, optional save).
  • Measured fidelity. Optimizations report a geometric deviation bound and the visual-fidelity SSIM of four fixed-camera renders before vs after, gated on the profile's minSsim floor. A failing SSIM fails the report — and returns a reference | result | change-heatmap sheet of the weakest view so the agent can see where the loss is. compare_glb does the same for any two files, plus geometric alignment scores.
  • Know before you plan. capabilities reports which generation providers have keys, whether a KTX2 encoder is installed, versions, and profiles.
  • Checkable determinism. Every written file comes back with its sha256.
  • Read-only tools are annotated (readOnlyHint) so clients can auto-approve analyze / inspect / render / audit / compare / list.

Tools: capabilities, analyze_glb, inspect_report, render_preview, compare_glb, optimize_glb, ship_asset, audit_directory, extrude_image, export_stl, export_usdz, list_profiles, generate_image_to_3d, generation_status, meshy_create_task, meshy_task_status, meshy_download. Prompts: web-ready-mobile-hero, logo-keychain, audit-and-fix-folder.

Tool descriptions teach the routing that matters: flat artwork → deterministic extrusion (free, instant, exact); photographic/dimensional subjects → generation (fal.ai open models or Meshy); everything → budget-checked, perceptually verified optimization.

Docs: https://github.com/glbforge/glbforge