# Weapon Lab (pypi · weaponlab-mcp)

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

- Trust score: 48/100 (low)
- Registry status: active
- Liveness: live
- Owner verified: no
- Last scored: 2026-10-16

## Components

- pypi · `weaponlab-mcp`: 48/100 (this document), [markdown](https://verifymcp.io/servers/hpdkhoa-weaponlab-mcp/weaponlab-mcp.md), [page](https://verifymcp.io/servers/hpdkhoa-weaponlab-mcp/weaponlab-mcp)

## Channel facts

- Registry: `pypi`
- Package: `weaponlab-mcp`
- Version: `0.1.0`
- Transport: `stdio`

## Trust breakdown

How this component scores in each security and reliability category. Every signal is checked automatically from public evidence about the published package, including repeated runs of it in an isolated sandbox, and we only credit what we can confirm. Scores are 0–100 per category. Scoring method: https://verifymcp.io/docs/scoring (what has changed: https://verifymcp.io/docs/scoring/changelog)

Scored 2026-10-16.

- **Supply Chain Security**: 50/100
  - Malware scan not yet available for this package.
  - No known CVEs affecting this package version or its production dependencies.
  - Runs hatchling.build at install time, a recognised build step with no custom scripting around it.
  - 1 of 29 dependencies flagged as unhealthy.
- **Provenance & Transparency**: 45/100
  - Source repository is publicly reachable at the declared URL.
  - Provenance check failed: no build-provenance attestation is published.
  - Clear OSI-approved license (MIT).
  - Actively maintained (last published 1 days ago).
  - Disclosure check failed: no security disclosure policy was found in the source repository.
- **Schema Quality & AI Usability**: 48/100
  - AI-judged instruction clarity (poor).
  - Tool/resource definitions use about 1427 tokens (~47/item across 30 items; 30 tools + 0 resources), lean.
  - Usage-examples check failed: none of the tools include examples.
- **Stability & Change Management**: 0/100
  - Stability not yet verified: not enough scan history yet (needs a 30-day window).
- **Tool Coverage**: 71/100
  - 100% of tools have a non-trivial description (not blank, and not just the tool's name).
  - 13% of tool parameters carry a description.
- **Tool Safety**: 100/100
  - No prompt-injection markers were found in the server instructions, tool names or descriptions we captured.
  - We read all 30 captured tool definition(s), and no name or description among them implies an irreversible operation.
  - An AI judge read all 31 captured unit(s) of tool text and found none that tries to manipulate the model reading it.
- **Capabilities**: 100/100
  - Implements a current MCP spec version (2026-07-28).

**Unverified: 1 category.** A category scored 0 because we could not verify it: a data source with nothing on this package, evidence we could not reach, or a check we could not run. We only credit what we can confirm.

## Install

### How do I install the Weapon Lab MCP server?

Weapon Lab runs locally as a PyPI package, launched with uvx weaponlab-mcp. Ready-made configuration for Claude, Cursor, VS Code, Codex and 5 more is on this page, copied from each client's own documentation.

### Claude

```bash
claude mcp add hpdkhoa-weaponlab-mcp -- uvx weaponlab-mcp
```

### Cursor

```json
{
  "mcpServers": {
    "hpdkhoa-weaponlab-mcp": {
      "command": "uvx",
      "args": [
        "weaponlab-mcp"
      ]
    }
  }
}
```

### VS Code

```json
{
  "servers": {
    "hpdkhoa-weaponlab-mcp": {
      "command": "uvx",
      "args": [
        "weaponlab-mcp"
      ]
    }
  }
}
```

### Codex

```bash
codex mcp add hpdkhoa-weaponlab-mcp -- uvx weaponlab-mcp
```

### opencode

```json
{
  "$schema": "https://opencode.ai/config.json",
  "mcp": {
    "hpdkhoa-weaponlab-mcp": {
      "type": "local",
      "command": [
        "uvx",
        "weaponlab-mcp"
      ],
      "enabled": true
    }
  }
}
```

### OpenClaw

```bash
openclaw mcp add hpdkhoa-weaponlab-mcp --command uvx --arg weaponlab-mcp
```

### Hermes

```yaml
mcp_servers:
  hpdkhoa-weaponlab-mcp:
    command: "uvx"
    args: ["weaponlab-mcp"]
```

### Netclaw

```json
{
  "McpServers": {
    "hpdkhoa-weaponlab-mcp": {
      "Transport": "stdio",
      "Command": "uvx",
      "Arguments": [
        "weaponlab-mcp"
      ]
    }
  }
}
```

### Vellum

```bash
assistant mcp add hpdkhoa-weaponlab-mcp -t stdio -c uvx -a weaponlab-mcp
```

### Other

```json
{
  "mcpServers": {
    "hpdkhoa-weaponlab-mcp": {
      "command": "uvx",
      "args": [
        "weaponlab-mcp"
      ]
    }
  }
}
```

## Changelog

Every change recorded for this component, newest first. Days that predate change tracking, or that we cannot explain, say so: "we were watching and nothing happened" and "we were not watching" are different claims.

### 2026-10-15 (score 48, +24)

- [security improvement] Injection markers: unverified → pass
- [security] First check of Judged manipulation: pass
- [security] Stability: Stability not yet verified: not enough scan history yet (needs a 30-day window).
- [functional improvement] Tool coverage: unverified → 100
- [functional improvement] MCP protocol: unverified → pass
- [functional] First check of Schema quality: fail
- [functional] First check of Schema quality: poor
- [functional] First check of Destructive annotations: pass
- [functional] First check of Schema quality: pass
- [functional] First check of Tool coverage: 13

### 2026-10-14 (score 24)

First indexed and scored.

## MCP tools (30)

### `project_info` (~29 tokens)

The project in use: its folder, data, specs and work folders, the probe command, Blender.

### `contract_check` (~53 tokens)

Checks a file a probe reads or writes against the probe contract.

Input parameters:

- `job_path`: for rows: the job they answer
- `kind` (string, required): job, rows or parts
- `path` (string, required)

### `spec_list` (~20 tokens)

Every weapon spec: marks, actions, marks still proposed.

### `spec_read` (~27 tokens)

One weapon's spec, with the default limits filled in.

Input parameters:

- `weapon` (string, required)

### `spec_validate` (~41 tokens)

Every problem with a spec, as sentences (empty: whole).

Input parameters:

- `spec`: a spec to check; or name a saved one
- `weapon`

### `spec_write` (~24 tokens)

Saves a whole spec and returns what changed.

Input parameters:

- `spec` (object, required)

### `gate_cases` (~39 tokens)

The cases (each a known bug as a metric, a weapon, an action and a pass rule).

Input parameters:

- `status`
- `weapon`

### `gate_metrics` (~22 tokens)

Every metric: provider, unit, which way is better, tolerance.

### `gate_weapons` (~13 tokens)

The project's weapons.

### `gate_add_case` (~40 tokens)

Adds or replaces a case.

Input parameters:

- `case` (object, required): {id, weapon, action, metric, rule {op, value}, about, source}

### `gate_run` (~51 tokens)

Measures the weapons with the providers (probe, rig, or the project's own) and stores the run.

Input parameters:

- `actions`
- `providers` (array, required)
- `staging`
- `weapons`

### `gate_verdict` (~43 tokens)

Pass only if the target cases pass, nothing else got worse past its tolerance and the checks are trusted.

Input parameters:

- `run_id` (string, required)
- `targets`

### `gate_set_baseline` (~31 tokens)

A run's rows become the baseline (merged over the old).

Input parameters:

- `run_id` (string, required)

### `gate_propose` (~60 tokens)

A staged change measured and judged; the proposal waits for a person's approval.

Input parameters:

- `actions`
- `name` (string, required)
- `providers` (array, required)
- `staging`
- `targets` (array, required)
- `weapons`

### `gate_approve` (~42 tokens)

Marks a passed proposal approved. Only on a person's word.

Input parameters:

- `approved_by` (string, required): who approved, in their words
- `proposal` (string, required)

### `gate_proposals` (~16 tokens)

Every proposal: passed, approved.

### `gate_evals` (~23 tokens)

Each provider's eval: faults caught, good cases passed, trusted.

### `probe_status` (~21 tokens)

The processes that must not run with the probe, running now.

### `probe_plan` (~27 tokens)

The job's weapons the probe would get.

Input parameters:

- `actions`
- `weapons`

### `probe_run` (~98 tokens)

One probe run: rows, and screenshots and parts dumps at the moments.

Input parameters:

- `actions`
- `at`: {action: [seconds]} for screenshots and dumps
- `parts`
- `shots`
- `slomo`
- `staging`: a folder whose stage.json overrides assets
- `tune`: {weapon: {field: value}}: a fix tried without writing it
- `weapons` (array, required)

### `rig_pieces` (~40 tokens)

A parts dump's pieces (triangles, centre, bounds, extents) and twins (a piece drawn twice).

Input parameters:

- `obj` (string, required)

### `rig_facts` (~41 tokens)

The weapon spec's facts (order, side, below, in) on a dump.

Input parameters:

- `obj` (string, required)
- `weapon` (string, required)

### `rig_align` (~67 tokens)

A magazine's line into its well over a reload's moments: worst offset and tilt while in the well.

Input parameters:

- `axis`
- `bone` (string, required)
- `moment_objs` (array, required)
- `seated_obj` (string, required)
- `well_depth_cm` (number)

### `rig_part_line` (~54 tokens)

A sliding part's path against its axis: line_cm and seat_cm.

Input parameters:

- `axis` (array, required)
- `bone` (string, required)
- `moment_objs` (array, required)
- `seated_obj` (string, required)

### `rig_fist` (~76 tokens)

A melee hilt against the fist's grip channel, and the turn and move that lay it in (try them with probe_run's
tune; a palm-down fist can hold the hilt right and still point the blade sideways: look at the screenshot).

Input parameters:

- `obj` (string, required)
- `side` (string)

### `motion_roll_profile` (~51 tokens)

The hand's roll about its forearm through a clip (0 thumb up; past 80 degrees breaks the forearm's range).

Input parameters:

- `fbx` (string, required)
- `side` (string)

### `motion_roll` (~67 tokens)

One clip's hand turned about its forearm, the twist bones sharing it.

Input parameters:

- `degrees` (string): a number, or auto: the clip starts thumb up
- `out_fbx` (string, required)
- `side` (string)
- `src_fbx` (string, required)

### `motion_roll_set` (~70 tokens)

A set of clips rolled, each from its own start, saved under new names (<name>_<suffix>).

Input parameters:

- `degrees` (string)
- `fbx_files` (array, required)
- `out_folder` (string, required)
- `side` (string)
- `suffix` (string, required)

### `motion_track` (~63 tokens)

A sliding part's track rebuilt on its axis from its seat.

Input parameters:

- `axis`
- `bone` (string, required)
- `out_fbx` (string, required)
- `root` (string, required)
- `seat`
- `src_fbx` (string, required)

### `motion_render` (~34 tokens)

Dev views of parts dumps (not the game's view).

Input parameters:

- `objs` (array, required)
- `out_folder` (string, required)

## Diagnostics

Captured diagnostic sections: Provenance, Install scripts, Dependencies. The full working is on the page: https://verifymcp.io/servers/hpdkhoa-weaponlab-mcp/weaponlab-mcp#diagnostics

## Score history

- 2026-10-16: 48
- 2026-10-15: 48
- 2026-10-14: 24

## Common questions

### What is the Weapon Lab MCP server?

Weapon Lab is an MCP server listed in the public MCP registry as io.github.hpdkhoa/weaponlab-mcp. Find and fix first-person weapon bugs behind a gate: your game's probe measures, the Gate judges. This page covers its PyPI package (weaponlab-mcp).

### Is the Weapon Lab MCP server safe to use?

Weapon Lab scores 48 out of 100 on VerifyMCP. We found no known CVEs affecting it as of 16 October 2026. That is a record of what we were able to check automatically, not an endorsement. The category breakdown on this page shows every signal behind the number, including the ones we could not confirm.

### What tools does the Weapon Lab MCP server expose?

Weapon Lab exposes 30 tools: project_info, contract_check, spec_list, spec_read, spec_validate, and 25 more. Their descriptions and schemas cost roughly 1,283 tokens of context every time the server is loaded.

### Is the Weapon Lab MCP server still maintained?

Weapon Lab is still listed as active in the MCP registry. We last reached this channel on 16 October 2026. Those dates come from our own scans of the registry and the channel itself, not from anything the publisher announced.

### What licence is the Weapon Lab MCP server under?

Weapon Lab declares the MIT licence, which is OSI-approved. That covers the source only, and says nothing about the cost of any service it calls.

## Links

- PyPI project: https://pypi.org/project/weaponlab-mcp/
- Socket report: https://socket.dev/pypi/package/weaponlab-mcp
- Repository: https://github.com/hpdkhoa/weaponlab-mcp
- Changelog RSS feed: https://verifymcp.io/servers/hpdkhoa-weaponlab-mcp/weaponlab-mcp.xml
- Changelog JSON feed: https://verifymcp.io/servers/hpdkhoa-weaponlab-mcp/weaponlab-mcp.json
- HTML version of this page: https://verifymcp.io/servers/hpdkhoa-weaponlab-mcp/weaponlab-mcp