Model Lab

io.github.hpdkhoaPublished by GitHub account hpdkhoav0.2.0Updated Oct 24, 2026

Draws rigged game gun models in Blender from parameters, checked against the real gun

The publisher's own server: model.tools — Zero-Auth Agent Utilities

VerifiedSTDIODesktop onlyDeveloper ToolsMedia & Design

Overview

AI-generated overview

Generates rigged AR-15-family game gun models in Blender from parameters, with self-checks and a photo-based outline comparison.

What you can do
  • List presets, platforms, parameters and rail/M-LOK attachment classes
  • Build a gun from a preset or platform with changed parameters, optionally with motion GIFs
  • Build measured animation clips (charge, fire, reload, stock positions) as FBX and GIF
  • Compare a build's outline against the bundled real-gun reference photo
  • List past builds and read their facts, marks and check results
When to use it
Useful when you need placeholder or prototype game weapon assets with rigs, attachment sockets and animation clips, and want the geometry checked against published dimensions and a reference photo. It suits game artists and developers working on AR-15-style rifles rather than anyone needing other weapon families or fabrication data.
Requirements
Runs locally over stdio as a Python package (modellab-mcp) via uvx or pip. Needs Python 3.10 or later and Blender 4.2 or later installed. Optional environment variables: MODELLAB_BLENDER for the Blender executable path, MODELLAB_OUT for the single output folder (defaults to ~/.modellab), and MODELLAB_WAIT_FOR to block builds while named processes run. Desktop only.
Before you install
Builds write files (FBX, .blend, PNG, JSON) to the folder set by MODELLAB_OUT, so point it at a location you are happy to have written to. It launches Blender as a local process, which can be heavy on the machine; MODELLAB_WAIT_FOR can hold builds back while other processes run. Output is limited to game-model shapes and moving parts, with no working internals or fabrication data, and many dimensions are estimates from photographs.

Installation

In SourceWeft

  1. Open Model Lab in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

Model Lab

Game gun models drawn in Blender from parameters, rigged and checked against the real gun.

[license: MIT] [Python 3.10+] [PyPI: modellab-mcp] [MCP Registry: modellab-mcp] [Blender: 4.2+] [tools: 10] [presets: 5 AR-15s]

An MCP server that draws game gun models in Blender from a few parameters. Each build has real parts at real proportions, one bone a moving part, its clips, and the facts a game needs. Every build checks itself, and a second check measures its outline against a photo of the real gun.

[An AR-15 with a holographic sight, a magnifier, a light and a vertical grip]

Ask for "an M4A1 with a red dot and a light on the right rail" and Model Lab writes a rigged FBX, an FBX for each attachment, a .blend, a sheet of pictures and a facts.json with every mark in gun space. It tells you which checks failed, if any. It makes game models only: outside shapes and moving parts. It draws no working internals and writes no fabrication data.

What a build gives you

You getWhat it is
SK_<name>_Rig.fbxthe gun on its rig: Bolt, ChargingHandle, DustCover, BoltCatch, MagRelease, Selector, Trigger, ForwardAssist, Magazine, MagRound, Stock, each with its real pivot and travel
SM_<name>_Magazine.fbxthe magazine alone, its origin on the feed lips, for the hand
one FBX an attachmentits origin on its recoil lug; SK_ when it has moving parts (folding sights, flip caps, a flip magnifier)
<name>.blendeverything, with the moving parts' cycle as an action
facts.jsonthe marks (chamber, port, magazine well, feed lips, grip, support hand, muzzle, sights), the rails and their slots, the attachments and their sockets, the parts table, every check
sheet.pnglabelled views: both sides, the top, the front, close views, the open action, the sight picture

Gun space: centimetres, +X the gun's left, +Y forward, +Z up. The origin is the bolt face at rest on the bore.

[An M4A1 from its right side]

Install

Model Lab needs Python 3.10 or later and Blender 4.2 or later.

uvx modellab-mcp

or

pip install modellab-mcp

Add it to your MCP client (Claude Code, Claude Desktop, or any client that runs stdio servers):

json
{  "mcpServers": {    "modellab": {      "command": "uvx",      "args": ["modellab-mcp"],      "env": { "MODELLAB_BLENDER": "C:/Program Files/Blender Foundation/Blender 4.2/blender.exe" }    }  }}
SettingWhat it does
MODELLAB_BLENDERBlender's executable. Leave it out when Blender is on the PATH or in its usual install folder.
MODELLAB_OUTThe only folder Model Lab writes to. Defaults to ~/.modellab.
MODELLAB_WAIT_FOROptional process names that hold the machine, such as UnrealEditor.exe,blender.exe. A build refuses to start while one runs. Off by default.
MODELLAB_IDLE_OKWith MODELLAB_WAIT_FOR: parts of a command line that mark a long-lived worker (default poselab_mcp). Such a worker counts only while it is busy.

The tools

ToolWhat it does
list_presetsThe ready guns: M4A1, M16A2, AR15, M4A1_Kitted, AR15_Optic.
list_platforms, describe_paramsThe gun families and every parameter: its range or choices, its unit, its meaning, and the sources of the real numbers.
list_attachmentsNine attachment classes for the rails and M-LOK slots.
build_gunBuilds a gun from a preset or a platform, with any parameter changed. motion=true adds GIFs of the cycle.
build_gun_clipsThe gun's own clips on a build's rig, measured, one FBX and one GIF each.
list_references, compare_to_referenceThe real-gun check: a build's outline against a photo.
list_builds, read_buildThe builds so far and their facts.

The same calls run from a shell: modellab presets, modellab build M4A1 stock_pos=2 name=MyM4, modellab clips <build>, modellab compare. Run modellab help for the list.

Every build checks itself

A build reports each check with its value. The checks:

  • the length against the published figure (the M4A1 at 29.75 and 33 in, the M16A2 at 39.63 in);
  • the chamber on the bore;
  • the dust cover: closed over the whole port, hinged on its bottom edge, and open against the lower, not through it (the build swings it a degree at a time and stops it where it first touches);
  • the magazine clear of its well's walls and seated;
  • the bolt's travel past the top round;
  • the sight line: the rear aperture and the front post at one height;
  • each attachment on a rail it fits, clear of the gun in every state, and its optic on the iron sight line;
  • every visible part with its real features (parts_complete). The parts table lists each part a person sees on the real gun and the features that make it read as that part: the charging handle's swept wings, finger hooks, latch and roll pin; the bolt catch's serrations; the castle nut's notches; the front sight base's bayonet lug, swivel and taper pins; and so on. A missing feature fails the build. Marks such as rail numbers are listed as texture, not shape.

[Close views: the charging handle]

The real-gun check

compare_to_reference draws the build's side outline at a reference photo's own scale. It lines the build up on the muzzle and the bore, measures both outlines column by column, and names the parts where they differ. The overlay shows the model in see-through red over the photo: dark photo showing through is real gun the model misses.

[The M4A1's outline over the reference photo]

This check found the faults the self-checks could not: the lower 1.55 cm too far back, the front sight base 2.4 cm back and the wrong shape, the stock's outline, the magazine's curve, and the rail's height. Now no stretch of the gun's outline over 1.75 cm long is more than 1 cm off. Attachments are classes, not the photo's exact models, so the check keeps their outline apart.

The reference ships with the package: a photo of an M4A1 carbine from PEO Soldier, File:M4A1-flattop.jpg on Wikimedia Commons, in the public domain as a work of the US Federal Government. The check reads its scale from the rail's teeth, 0.394 in apart.

Attachments on sockets

Each rail reports its slots at the Picatinny pitch (MIL-STD-1913), slot 0 at the rear. M-LOK handguards report their slots too (32 by 7 mm, 40 mm apart). Pass attachments by name, or as {item, rail, slot, state, options}:

{"preset": "M4A1", "params": {"attachments": [{"item": "flip_rear", "state": "down"}, "red_dot", "weapon_light"]}}

The nine classes: folding rear and front sights, the M4's carry handle, a 30 mm red dot with flip caps, a holographic sight, a 3x magnifier on a flip mount, a 4x32 prism sight, a vertical grip, a weapon light. A build checks that each fits its rail, clears the gun in every state, and clears the others as shown. When one blocks another's move, the build lists it: behind a magnifier, the rear sight goes up only after the magnifier swings aside.

[The sight picture through a red dot, the A2 post in its middle]

Motion and clips

Every .blend holds the cycle as an action. motion=true renders it as GIFs: the charging handle drawn back, the cover springing open, the carrier flying home, the magazine out and in, then the attachments' own moves.

[The cycle on an AR-15 with a magnifier and a holographic sight]

build_gun_clips keys the gun's clips at 60 frames a second from real timings: charge, chamber check, fire (a 75 ms cycle), the last shot (the bolt held on its catch), reload, empty reload, and the stock's positions. Each clip is measured: every part on its own axis, the full stroke, the cover open before the carrier has moved 1 cm, the magazine out of the well and seated, the bolt held until the magazine is in.

[An empty reload: the bolt held open until the new magazine is seated]

Next: soft edges where a hand holds

The owner, 2026-10-21: "the grip is no sharp edge, this will be the next improvement for Model Lab when read on the manual or images, make the corner round a bit, especially the places that human grab and hold, most of the time they will no sharp edge because sharp edges will hurt the hand/human, make them softer so hand can hold it".

  • Every part a hand grabs or holds gets rounded edges: the grip, the pistol grip's panels, the handguard, the magazine, the charging handle, the stock's cheek and butt.
  • Each radius is read from the manual, drawing or photo when it shows one. Otherwise it comes from a named human-engineering source, recorded with the part.
  • The real-gun check compares these edges too.

Why it matters, measured: on a digitized M1911A1 the grip safety was a square extrusion. A hand placed on the grip had the safety's edge 0.42 cm in its palm (the palm gives 0.27 cm). Rounding the grip parts by 0.75 mm, the least MIL-STD-1472G 5.7.7.6 allows, cut that to 0.09 cm past the give. Red: before (sharp). Blue: after (rounded). Below, close-ups of the spot before and after.

[The palm's clip against the grip safety, sharp and rounded]

Limits

  • One platform so far: the AR-15 family. Others will follow.
  • One reference photo: the M4A1 from its right side.
  • The clips are the gun's side only. A hand's clips need an arms rig.
  • No selector clip yet: the lever's direction at SAFE is not yet checked against a source.
  • Many numbers are estimates sized from photographs. describe_params lists every source and every estimate.

Trademarks

M-LOK is a trademark of Magpul Industries. Model Lab draws M-LOK slots to their published dimensions and is not connected with Magpul. AR-15 is a trademark of Colt's Manufacturing; here it names the rifle family in its common sense. Military designations (M4A1, M16A2, M68) name the guns and parts Model Lab copies. No product is endorsed.

License

MIT. See LICENSE.

Source: README.md at commit b5098b8

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

2
  1. v0.2.0LatestOct 15, 2026
  2. v0.1.0Oct 14, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts

Other Model integrations