SpatialPack — 3D asset readiness runs on your own machine — the client starts it, so there is no endpoint to ping. 23 installs a week from npm.
Test whether 3D assets survive Apple Quick Look and Safari <model>, then fix what fails
Today is the operative word: we check SpatialPack — 3D asset readiness every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.
This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.
claude mcp add mcp -- npx -y @spatialpack/mcp
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@spatialpack/mcp"
],
"command": "npx"
}
}
}
[mcp_servers.mcp]
command = "npx"
args = ["-y", "@spatialpack/mcp"]
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@spatialpack/mcp"
],
"command": "npx"
}
}
}
{
"mcpServers": {
"mcp": {
"args": [
"-y",
"@spatialpack/mcp"
],
"command": "npx"
}
}
}
This one needs environment variables set before it will start:
SPATIALPACK_MCP_SANDBOX (Sandbox root for asset reads and writes, equivalent to --sandbox. Defaults to a per-process temp directory.), SPATIALPACK_MCP_LOG (Log level for the JSON-Lines diagnostic stream on stderr: debug, info, warn, error, or silent. Defaults to info.).
The author declared them in the registry entry; get the values from the project itself.
BYOK, fully local AI agent that tests your app/API and writes a real Playwright spec on success.
Shared app-testing runbook: read the plan, record results per platform, raise and fix issues.
Paid remote MCP for synthetic user testing, UX validation, analytics, checkout, and readiness.
Disposable test mailboxes on a real domain: send, receive and assert on real email.
Audits tests instead of writing them: what each one really asserts. 4 tools, local.
Real UK MOT failure data by car model and mileage, aggregated from official DfT test results.
Agents that test your web and mobile app like real users, on every pull request.
Discover, shortlist, compare, cost-model, and live-test 300+ AI models from your editor
Answers built from our own checks of this server.