MCP server for interacting with the Scryfall MTG API
Nothing to run from here
Model Lab is installed from its publisher's own source and answers where it runs, so this marketplace is not in the path of a single call. There is no address here to send one to, and a panel that pretended otherwise would be showing you an answer we made up. Install it and call it from your own client — the Installation tab has the entry for each one.
93/100
trust score
10
tools declared
local
runs on your machine
—
downloads a day
What it does
Draws rigged game gun models in Blender from parameters, checked against the real gun
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user model-lab-mcp '--' uvx modellab-mcp
# 2 — ask your agent for something these tools do
# list_platforms, describe_params, list_presets and 7 more
Model Lab costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publishernot claimed
HPAll 5 servers
hpdkhoa5 servers
3 categories
Collected from a public index. Nobody has claimed this account, so nothing here was written by its author — claim it if it is yours.
Installation
Where are you running it?
Every route below installs the same thing and ends at the same approval screen. This one runs on your machine: your client starts Model Lab as a process under your own user, with your files and your network, so the tool surface below is what it can do to your computer rather than to a server somewhere else. Its scan result is on the Security tab — read the surface before you approve it.
Claude Codedeclared by this listing
This is a public server: you run it yourself and this marketplace is not in the path. You need uv (docs.astral.sh/uv): uvx comes with it. Claude Code registers it in one command; --scope user makes it available in every project. The '--' is in quotes so that PowerShell passes it on.
claude mcp add --scope user model-lab-mcp '--' uvx modellab-mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
Free on mcprush, and it runs from its publisher’s own package: this marketplace is not in the path, so there is no key of ours to hold and no card to add.
What it asks of you
Nothing is required, but it can take MODELLAB_BLENDER (Blender's executable (4.2 or later), if it is not on the PATH or in the usual install folder), MODELLAB_OUT (The only folder Model Lab writes to (builds, clips, comparisons); defaults to ~/.modellab), MODELLAB_WAIT_FOR (Optional process names that hold the machine (e.g. UnrealEditor.exe,blender.exe); a build refuses to start while one runs) if you want to set them.
What it writes
One config entry your client uses to start the process locally. A local server runs with your file system and your network, which is why it is priced without metering.
What you approve
10 tools, with what each one reads, writes and reaches shown before you agree — the same list on every route above. Read the tool surface.
Tool surface
What the model actually sees. Descriptions are diffed on every release — see version history.
The gun families Model Lab can draw, with their parameter names.
No parameter schema on file.
A platform's parameters (type, range or choices, unit, meaning) and the sources its real numbers come from.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| platform | string | no | a platform id, e.g. ar15 |
The ready guns (M4A1, M16A2, AR15, M4A1_Kitted, AR15_Optic): their parameters and the published lengths each build is checked against.
No parameter schema on file.
The attachments a build can mount on the rails and M-LOK slots (optics, backup sights, the carry handle, a vertical grip, a light): what each is, the rails it fits, its states and moving parts. Pass them to build_gun as params.attachments.
No parameter schema on file.
The real-gun photos compare_to_reference measures against: each photo's source, licence, scale and the build that matches it.
No parameter schema on file.
Builds a gun in Blender (15 to 30 s): the rig FBX, the hand magazine FBX, one FBX an attachment, the .blend (with the cycle as an action), facts.json and a sheet of labelled dev views; with motion, GIFs of the cycle.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| preset | string | no | a preset to start from, e.g. M4A1 |
| params | object | no | parameters to set or change, e.g. {"barrel_in": 16} |
| name | string | no | the model's name in its files (letters, digits, _) |
| scale | number | no | the whole model's scale; 1 is real size |
| platform | string | no | without a preset: the platform to build |
| motion | boolean | no | also render the moving parts' cycle as GIFs (about a minute more) |
The gun's own clips on a build's rig, from real beats and timings at 60 frames a second: each measured (parts on their axes, the bolt's stroke, the cover open before the carrier, the magazine out of the well and seated, the bolt held on its catch), exported alone as FBX (A_<name>_<clip>.fbx) and…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build | string | yes | a build folder name from list_builds |
| clips | array | no | charge, chamber_check, fire, fire_last, reload, reload_empty, stock; leave out for all |
| render | boolean | no | render a labelled GIF a clip |
The real-gun check: draws the build's side outline at the reference photo's scale and alignment, measures both outlines column by column, and returns the stretches that differ by more than 0.4 cm, each with the parts there and its zone (the gun, or an attachment over the rail), and an overlay…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| reference | string | no | a reference id from list_references |
| build | string | no | a build folder; leave out to build the reference's own configuration |
The latest builds, newest first: name, whether every check passed, size.
No parameter schema on file.
A build's facts: parameters, marks, moving parts, rails, attachments, the parts table, every check, files.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| build | string | yes | a build folder name from list_builds |
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source published under MIT
- Runs on your machine — nothing of it reaches our gateway
- Nothing to cap, because mcprush bills nothing
What counts against your monthly calls
| Tool | Unit | Calls used | Out of the allowance |
|---|
Nothing here is billable: mcprush charges nothing to install Model Lab or to call it, at any volume.
Call allowance · this installenforced at the gateway
Monthly allowance, in calls
—
—
Alert at 80% · then the tool returns a normal MCP error
Used this month: —
ATrust score 93 / 100
Release 0.2.0 · scanned 15 Oct 2026
Two independent axes, because powerful and malicious are different questions. The grade is threat only. The capability level is blast radius, and it is never a penalty on the grade — it is priced as one subtract-only term in the score, where you can see it.
Threat score100
Client score93
Findings3 threat · 0 capability
Capabilityhigh
Coveragesource
Verificationrepo
Surface digest18dcfbc2d476e6fe8b2c4f0151d200158c4db6df87888ed171f999d01752f4b6
Score vectorthreat 100 → client 93
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | high | capability blast radius (high) — client exposure if the model is manipulated | −6 |
| verification-discount | repo | publisher verification (public source) — no provenance, but the source is public and inspectable | −1 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
score = clamp(round(threatScore − E_cap − E_ver − E_cov), 0, 100). No model, no opinion, no network call at scoring time: the same methodology version against the same bytes always produces this number, and every line above is a field of the report rather than a summary of it.
What the scan could actually read
A grade is only as meaningful as its coverage, so the scanner publishes its own depth before it publishes its result.
Tool surfaceread
Implementation sourceread
Package metadataread
Live transportnot available
Tools were statically extracted from the published source (10 recovered), not enumerated from a running server. Tool-poisoning, Unicode-smuggling, capability and toxic-flow analysis ran on this inferred surface, but a mis-parsed registration could be missed or mis-attributed, so tool-derived findings are capped below “confirmed”. To grade the real runtime surface, scan the running server: --command "npx -y <package>".
Capability — what it could do if the model were manipulated
Tags derived from each tool’s schema and the implementation, not from what the tool calls itself. high is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| list_platforms | no tags | |
| describe_params | no tags | |
| list_presets | no tags | |
| list_attachments | no tags | |
| list_references | no tags | |
| build_gun | no tags | |
| build_gun_clips | no tags | |
| compare_to_reference | no tags | |
| list_builds | no tags | |
| read_build | no tags |
Toxic-flow graph
The lethal trifecta, checked as a graph rather than as a checklist: untrusted input, a sensitive source and an external sink have to meet before there is a path worth worrying about.
The public result for this release does not print the flow graph, so there is nothing to show here. That is not the same as "no paths were found": what the scan did read is above, under coverage.
Supply chain and provenance
Integrityfirst-seen
Surface digest18dcfbc2d476e6fe
Scanned2026-10-15
This is the first scan of this surface here, so there is nothing yet to compare it against.
Every result on this tab comes from one deterministic pass over the published package — offline, rule by rule, and auditable line by line above. Same methodology version, same bytes, same score.
Release history
Always latest — the install command names no version, so it installs the newest release when it runs; the current release on file is 0.2.0. Pin a release below and the command asks for exactly that one.
0.2.0
undated
latestNo release note was published with this version.
—
no reviews yet
Who can review
One review per account, from a signed-in account that does not publish this listing. Nothing else is asked — you can say what you think before you install it. Publishers can reply once per review, and a review can be edited or deleted by whoever wrote it.
Sign in to write one
Any signed-in account that does not publish Model Lab can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
No reviews yet
Nobody has reviewed this listing. The rating on the card is the mean of the reviews written here and nothing else, so there is no rating until somebody writes the first — which takes a signed-in account that does not publish it, and nothing else.