MCP server for interacting with the Scryfall MTG API
Nothing to run from here
GrowBlocks Dev Kit 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.
96/100
trust score
23
downloads a day
local
runs on your machine
232
downloads in 30d
What it does
GrowBlocks Dev Kit lets your coding agent build three.js browser games and ship them to GrowBlocks (growblocks.xyz), straight from your own machine. Your agent can start a new game from the starter, add ready-made blocks (boost pads, neon gates, skylines and more), run checks and play-test with screenshots, then push builds and submit the game for review. 22 tools in all, plus prompts for making and shipping a game, and the Dev Kit API docs and types as resources. Runs locally over stdio with npx. Building needs no account; sign in with growblocks_login only when you push or submit. Docs: https://growblocks.xyz/devkit.html
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user growblocks-dev-kit-mcp '--' npx -y growblocks mcp
# 2 — ask your agent for something these tools do
# growblocks_docs, growblocks_check, growblocks_whoami and 19 more
GrowBlocks Dev Kit costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
Publisher
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 GrowBlocks Dev Kit 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 Node.js — the current LTS (24) is the safe choice; npx 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 growblocks-dev-kit-mcp '--' npx -y growblocks 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 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
22 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.
Read from its source code. A server that builds its tool list when it starts can list more tools than this.
The GrowBlocks Dev Kit API for writing game.js (llms.txt): the contract, every gb.* call, patterns and pitfalls. Read it before writing game code. Pass topic (e.g. "gb.physics", "gb.net", "Pitfalls") to get one section.
No parameter schema on file.
Run the Dev Kit checker on the game folder. play=false: static checks (syntax, unknown gb.* calls, blocked browser APIs, imports, file limits). play=true: also plays the game headless inside GrowBlocks for some seconds, reports every runtime error and returns a screenshot. Run it after every…
No parameter schema on file.
Who the GrowBlocks CLI is signed in as, and how many games they have. Fails with "Not signed in" if login is needed.
No parameter schema on file.
Start signing in to GrowBlocks. Returns a link and a code: give both to the human, who opens the link, checks the code, signs in with Google and presses Allow. The sign-in finishes in the background; check it with growblocks_whoami.
No parameter schema on file.
The signed-in developer's games: status (draft, in review, live, changes needed), test and live builds with their links, and GrowBlocks' review note.
No parameter schema on file.
The status of the game this folder is linked to (growblocks.json): builds, links, review state and note, and what to do next.
No parameter schema on file.
Create a new game on GrowBlocks and link the folder to it. address: 3-32 lowercase letters, numbers and dashes (its URL, game.html?g=<address>). Ask the human for the name and address first. A logo (WebP, under 22 KB) and a description are needed before submitting.
No parameter schema on file.
Link the folder to one of your existing games (writes growblocks.json).
No parameter schema on file.
Change the linked game's name, tagline, description, studio (the name shown after "by"; empty = the developer's account name), players per room or logo.
No parameter schema on file.
Run the static checks, then upload the folder as a new test build of the linked game. Returns the unlisted test link to play and share. Does not make anything public. At most 20 uploads per game a day, so push when a change is worth testing.
No parameter schema on file.
Submit the latest test build to GrowBlocks for review (needs a logo and a description). Only do this when the human asks: GrowBlocks plays it and approves it or sends a note.
No parameter schema on file.
Search the GrowBlocks blocks: parts of games other developers published (vehicles, game modes, enemy brains, level kits) that a game can add instead of writing them. Look here before building something common. Pass words to search names, descriptions and tags.
No parameter schema on file.
One block: what it does, its versions (and what it forked), its entry file and which live games use it.
No parameter schema on file.
Add a block to the game: copies its files into blocks/<slug>/ and records it in growblocks.json. Then import it from ./blocks/<slug>/<entry> and read its code for how to use it. Do not edit the block files: GrowBlocks recognises the block by them and its author earns from the game (paid by…
No parameter schema on file.
Publish the folder as a block. It needs block.json (slug, name, description, entry, tags, and forkOf if it started from another block). Others can then add it, and its author earns from every live game that ships it. Only when the human asks.
No parameter schema on file.
Create a new game folder from the latest starter kit (game.js, play.html, check.mjs, llms.txt, gb.d.ts, this CLI and .mcp.json). Then pass that folder as dir to the other tools.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| folder | string | yes | — |
The whole gb API for game.js: the contract, every call, patterns and pitfalls.
No parameter schema on file.
The same API as TypeScript types.
No parameter schema on file.
Build a browser game on GrowBlocks from an idea, checking it with a screenshot until it plays well.
No parameter schema on file.
What the game is, in a sentence or two.
No parameter schema on file.
Folder to make it in (default: a new one named after the idea).
No parameter schema on file.
Check the game in this folder, upload a test build and say how to get it reviewed.
No parameter schema on file.
Free
$0 forever
- Every tool, no call limit
- No card, and mcprush charges nothing for it
- Source is public; its licence metadata reads NOASSERTION rather than naming a licence
- 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 GrowBlocks Dev Kit 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 96 / 100
Release 1.2.0 · scanned 17 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 score96
Findings1 threat · 0 capability
Capabilitymoderate
Coveragesource
Verificationrepo
Surface digestc84e77dda125ed8d0f70e6df8f002f622392f04ba176427ff1c3701253418c7b
Score vectorthreat 100 → client 96
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| 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 (16 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. moderate is the level these add up to.
| Tool | Capability tags | Why the tag was assigned |
|---|---|---|
| growblocks_docs | no tags | |
| growblocks_check | no tags | |
| growblocks_whoami | no tags | |
| growblocks_login | no tags | |
| growblocks_games | no tags | |
| growblocks_status | no tags | |
| growblocks_create_game | no tags | |
| growblocks_link_game | no tags | |
| growblocks_update_game | no tags | |
| growblocks_push | no tags | |
| growblocks_submit | no tags | |
| growblocks_blocks | no tags | |
| growblocks_block_info | no tags | |
| growblocks_add_block | no tags | |
| growblocks_publish_block | no tags | |
| growblocks_new_game | 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 digestc84e77dda125ed8d
Scanned2026-10-17
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 1.2.0. Pin a release below and the command asks for exactly that one.
1.2.0
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 GrowBlocks Dev Kit 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.