Swipium runs on your own machine — the client starts it, so there is no endpoint to ping. 103 installs a week from npm. Last commit 20 Oct 2026.
Mobile QA on local Android Emulators and iOS Simulators: autopilot tests, evidence, reports.
We read the source, 4 d ago · rules 995398eba69f
What this server is able to do. For an MCP server this is often the job itself — a terminal server runs commands because that is what it is for. Listed so you know what you are plugging in, not as an accusation.
? `left unchanged: it is not a valid registry (${projects.corrupt}); fix or delete it`
: projects.removed
? `${args.dryRun ? 'would prune' : 'pruned'} ${projects.removed} stale of ${projects.before} entr${projects.before === 1 ? 'y' : 'ies'} (${projects.after} left)`
const child = spawn(resolveAndroidTool('emulator'), emulatorBootArgs(avd, headless), {
Is this your server and something here is wrong? Tell us — corrections are free and do not require a plan.
We found places where it runs commands, builds paths or queries from values it is given. None of that is a flaw by itself — it becomes one when the code changes, and code changes quietly between releases. We re-read it on every one.
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 swipium -- npx -y swipium
{
"mcpServers": {
"swipium": {
"command": "npx",
"args": [
"-y",
"swipium"
]
}
}
}
[mcp_servers.swipium]
command = "npx"
args = ["-y", "swipium"]
{
"mcpServers": {
"swipium": {
"command": "npx",
"args": [
"-y",
"swipium"
]
}
}
}
{
"servers": {
"swipium": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"swipium"
]
}
}
}
Optional settings from the registry entry, left out of the block above:
SWIPIUM_PROJECT_ROOT (Absolute path of the mobile app repo when the client exposes no workspace root), SWIPIUM_TEST_EMAIL (Test account email or username for login flows), SWIPIUM_TEST_PASSWORD (Test account password for login flows).
Real product evidence: 281k+ real app screens and flows, 20k+ mobile A/B tests, growth reports.
Local QA workflows, test evidence, screenshot maps and confidence reports for AI coding agents.
Per-term sealed grant spend evidence; reports recompute from receipts, local/simulator.
AI testing harness with Jay: risk-based checks, bug investigation, and local evidence reports.
Isolated macOS app tests, MCP images, OCR/ASCII frames, accessibility and evidence reports.
Report local task-scoped test and build residue without cleaning resources.
Deep Research MCP for multi-round investigations, traceable evidence, and cited reports.
Local job-search tracker: roles, a status machine with evidence, rules, interviews, daily reports.
Answers built from our own checks of this server.