Blender integration through the Model Context Protocol
Ballmac 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.
What it does
Search, inspect and install Ballmac UI React and Tailwind components, blocks and templates.
Quickstart
# 1 — add it to Claude Code
claude mcp add --scope user ballmac-mcp '--' npx -y @ballmac/mcp
# 2 — ask your agent for something these tools do
# list_items, list_categories, search_items and 9 more
Ballmac costs nothing on mcprush: there is no plan to choose here, no cap to set and nothing mcprush can bill you for.
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 Ballmac 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.
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 ballmac-mcp '--' npx -y @ballmac/mcpReconnect, or start a new session, and the tools appear in the model’s tool list.
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.
12 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.
List components, blocks or templates, optionally filtered by kind, category (a component category such as primitives, motion or ai; a block section such as hero or pricing; or a template kind such as marketing) or tier. Call list_categories for the valid names.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| kind | string | no | — |
| category | string | no | — |
| tier | string | no | — |
How many components, blocks and templates there are, and the categories each is grouped into, with counts. Use the names as the category filter of list_items.
No parameter schema on file.
Search by what the user needs (for example 'chat input with attachments', 'animated stat', 'pricing section', 'online store'). Understands common synonyms such as modal, navbar or ecommerce. Returns the best matches with when-to-use guidance.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| query | string | yes | — |
| kind | string | no | — |
| limit | integer | no | — |
Everything about one item: description, when to use and not, import line, props, keyboard behaviour, dependencies, composition hints, template pages and the full source (for Pro items only when the server has BALLMAC_LICENSE_KEY; see the licence field). Set includeSource to false for a shorter…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| includeSource | boolean | no | — |
Working example code for an item (the same examples shown on its page).
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
The changelog of an item: what changed in each version, newest first, and whether anything is breaking. Pass since (the version the user has, for example from ballmac.lock.json) to see only newer changes. Use it before updating an installed item; npx @ballmac/cli outdated lists which installed…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
| since | string | no | — |
The vitest + Testing Library test file that ships with an item (keyboard use, states, ARIA). Use it to check an item still works after you or the user changed it. npx @ballmac/cli add <name> --with-tests installs it next to the component with the packages and config it needs, and `npx…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| name | string | yes | — |
The rules audit_project checks, with why each matters, how to fix it and a bad and a good example: missing loading, empty and error states, unlabelled controls, removed focus outlines, fixed colours instead of theme tokens, endless motion, layouts that overflow a phone. Read it BEFORE writing UI…
No parameter schema on file.
Read the project's React source (it never writes or runs anything) and report what people and assistive technology trip over: components that can show loading, empty and error states but are used without a state prop, data fetched with no loading or error handling, icon-only buttons with no name,…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| path | string | no | The project folder. Defaults to the folder this server was started in. |
| paths | array | no | Limit the audit to these files or folders, relative to the project folder, for example ["src/components/header.tsx"]. |
| minSeverity | string | no | The weakest severity to list. Default warn. Counts always include everything. |
| limit | integer | no | How many findings to return (default 50). |
| includeLibrary | boolean | no | Also audit components/ui and components/ballmac (installed library code). Off by default. |
The shadcn CLI commands to add one or more items to the user's project. setup is optional: a current shadcn CLI resolves @ballmac without it, so run it only for an older CLI. Then run add. byUrl works without setup for free items. Pro items install as @ballmac-pro/<name> and need proSetup…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| names | array | yes | — |
| packageManager | string | no | — |
Plan a page from Ballmac UI blocks for an intent such as 'SaaS landing page with pricing and FAQ' or 'login screen'. Returns the chosen blocks in page order, install commands, a page.tsx scaffold that renders them, and any complete templates that already fit the intent. When the request names…
| Parameter | Type | Required | Notes |
|---|---|---|---|
| intent | string | yes | — |
| packageManager | string | no | — |
| includePro | boolean | no | — |
| feel | string | no | Platform feel to build for. Omit to let the intent decide: macOS, Windows, iOS, Tauri or Electron in the request pick one. |
How to prepare a project for Ballmac UI (shadcn init, optional theme, and the registry entry older CLIs need) and its requirements.
| Parameter | Type | Required | Notes |
|---|---|---|---|
| packageManager | string | no | — |
- 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 Ballmac or to call it, at any volume.
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.
| Term | Level | What it prices | Points |
|---|---|---|---|
| capability-exposure | moderate | capability blast radius (moderate) — client exposure if the model is manipulated | −3 |
| verification-discount | source | publisher verification (provenance) — cryptographic build provenance ties the artifact to its source | −0 |
| coverage-honesty | source | inspection depth (source) — how much of the target the scan could see | −0 |
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.
Tools were statically extracted from the published source (12 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 |
|---|---|---|
| list_items | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| list_categories | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| search_items | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_item | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_examples | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_changes | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_tests | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_quality_rules | no tags | |
| audit_project | no tags | |
| get_install_command | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| compose_page | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
| get_setup | untrusted-input | untrusted-input: declares openWorldHint: true (interacts with entities outside the server) |
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
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 1.4.0. Pin a release below and the command asks for exactly that one.
No release note was published with this version.
- The version this listing was on when mcprush began following its releases. The registry was not asked when it shipped, so this row carries no date.
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.
Any signed-in account that does not publish Ballmac can review it, once — before installing it or after. A review from an account that has installed it is marked as one.
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.