Weapon Lab

io.github.hpdkhoaPublished by GitHub account hpdkhoav0.1.0Updated Oct 24, 2026

Find and fix first-person weapon bugs behind a gate: your game's probe measures, the Gate judges

VerifiedSTDIODesktop onlyDeveloper ToolsMedia & Design

Overview

AI-generated overview

MCP server for game developers that turns first-person weapon bugs into gated cases, measures them via your game's probe, and judges fixes.

What you can do
  • Manage bug cases: run the gate, get verdicts, propose and approve changes, set baselines, list cases
  • Run your game's probe, plan and check its status, try fixes by tuning, staging assets or screenshots
  • Inspect a posed weapon from a parts dump: pieces, real-world facts, magazine alignment, hilt in fist
  • Rebuild and render motion clips in Blender, rolling a hand about its forearm or sliding a part on its axis
  • Read, validate and write per-weapon spec files, and check probe job, rows and parts files against the contract
  • Rig any gun model for 18 actions, build and verify clips, and trace a real gun's blueprint from public sources
When to use it
Use it when you are fixing first-person weapon problems in a game — hands off the gun, a crooked magazine, a misheld blade, arms covering the screen — and want each fix measured and gated rather than eyeballed. It suits teams that can write a small probe for their engine.
Requirements
Python 3.10 or later, installed as the weaponlab-mcp package and run as a local stdio process. A project folder containing weaponlab.json, set via WEAPONLAB_PROJECT (current folder by default). Blender 4.4 or later for Motion Lab and renders, located via WEAPONLAB_BLENDER or the PATH. Hand bones must use Unreal mannequin names for fist and forearm measures.
Before you install
It never runs your game itself: you must write a probe that follows the contract, and it acts on what the probe writes back. The gate records approvals and can stage assets and write spec files in your project, so review proposed changes before approving. Blender is launched for Motion Lab and renders.

Installation

In SourceWeft

  1. Open Weapon 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

Weapon Lab

First-person weapon bugs fixed once per kind, then for every weapon, behind a gate.

[license: MIT] [Python 3.10+] [PyPI: weaponlab-mcp] [MCP Registry: weaponlab-mcp] [Blender: 4.4+ (Motion Lab)] [tools: 67] [probe contract: v1]

An MCP server that finds and fixes first-person weapon bugs behind a gate: hands off the gun, a magazine crooked in its well, a blade held wrong, arms covering the screen.

Each bug becomes a case: a metric, a weapon, an action and a pass rule. Your game's own probe measures the weapons. The Gate passes a change only when its target cases pass and nothing else got worse. Fix each kind of bug once, then check every weapon with it.

Weapon Lab never runs your game itself. You write a small probe for your engine that follows the probe contract: a job file in, a rows file out. Everything else works on what the probe writes back.

What it does

GroupToolsWhat for
Gategate_run, gate_verdict, gate_propose, gate_approve, gate_set_baseline, gate_cases, ...Keeps the bugs as cases, measures, compares against a baseline, judges a change, records a person's approval.
Probeprobe_run, probe_plan, probe_statusStarts your game's probe. Tries a fix before it is written: tuned fields, staged assets, screenshots, parts dumps.
Rig Labrig_pieces, rig_facts, rig_align, rig_part_line, rig_fistReads the posed weapon from a parts dump: its pieces, real-world facts (the magazine behind the barrel), a magazine's line into its well, a hilt in the fist.
Motion Labmotion_roll, motion_roll_profile, motion_roll_set, motion_track, motion_renderRebuilds clips in Blender: turns a hand about its forearm inside the forearm's range, puts a sliding part back on its axis.
Specsspec_list, spec_read, spec_validate, spec_writeOne file a weapon: marks (grip, support), anchors (pieces to find), facts, limits.
Contractcontract_checkChecks a probe's job, rows or parts dump.
Gun Kitgunkit_inspect, gunkit_draft, gunkit_from_modellab, gunkit_proxy, gunkit_rig, gunkit_build, gunkit_verify, gunkit_export, gunkit_cases, gunkit_actions, gunkit_actionTakes any gun model to the game: rigs it for one of 18 actions, makes its own clips and the hand clips on one shared pair of arms, checks them, stages the files. See docs/GUNKIT.md.
Blueprint Labblueprint_source_add, blueprint_scan, blueprint_specs, blueprint_figure_add, blueprint_calibrate, blueprint_trace, blueprint_part, blueprint_check, blueprint_build, blueprint_to_gunkit, ...Makes a real gun's visual copy from its public sources (manuals, patents, photos): facts from the data tables, outlines traced from scaled figures, a blueprint with the source of every number, the model built in Blender. See docs/BLUEPRINT.md.

Try it on the demo

The demo is a toy game with two planted bugs and a probe in about 150 lines. It needs no engine.

bash
pip install -e .cd examples/demoweaponlab gate run probe,rig

(python -m weaponlab works the same when pip's scripts folder is not on your PATH.)

The rifle's left hand misses its handguard by 3.75 cm. The knife's hilt lies 90 degrees across the fist. tests/test_demo.py walks the whole loop: measure, find the fix, try it by tune, judge it.

Use it in your game

  1. weaponlab init in your project. It writes weaponlab.json and empty data files.
  2. Write your probe from the contract, starting from examples/demo/probe/demo_probe.py. Set its command in weaponlab.json.
  3. List your weapons in weaponlab/data/weapons.json and their actions in actions.json.
  4. Add a case for each bug you know. Measure everything once and set the baseline.
  5. Fix through the loop: try by tune or staging, look at the screenshots, propose, approve, import.

Check your probe on its own with weaponlab contract job|rows|parts <file>.

Add it to an MCP client

json
{"mcpServers": {"weaponlab": {"command": "weaponlab-mcp", "env": {"WEAPONLAB_PROJECT": "C:/path/to/your/game"}}}}
SettingMeaning
WEAPONLAB_PROJECTThe project folder with weaponlab.json. The current folder by default.
WEAPONLAB_BLENDERBlender, for Motion Lab. Found on the PATH or in the usual install folders otherwise.

Requirements

  • Python 3.10 or later.
  • Blender 4.4 or later for Motion Lab and renders. Nothing else needs it.
  • Hand bones named as Unreal's mannequin names them (hand_r, index_01_r, lowerarm_r) for the fist measure and the forearm roll.

Where it came from

Weapon Lab is the general part of the tools built for ToangTown, an Unreal 5.8 game with 46 weapons. Its first probe is ToangTown's. The contract's lessons come from that probe. Pose Lab (poselab-mcp) answers the body's side: clipping, the view, a grip solver. The Gate can use it as a provider.

License

MIT

Source: README.md at commit 6a8dc92

Tools

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

Version history

1
  1. v0.1.0LatestOct 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