MCP server for simulator-based mobile QA agents

QA Tools for Your Agent

Test and catch issues before the build.

Swipium is free and open source. It exposes simulator-based mobile QA as structured MCP tools so agents can launch apps, inspect screens, execute UI actions, collect evidence, build app maps, generate reports, and create reusable test assets.

GitHub X Follow Swipium

Quick start

npx -y swipium verify

npm install -g swipium
swipium init codex --apply

What it is

An agent-facing QA harness.

Swipium runs locally as a stdio MCP server. Agents communicate with it through structured JSON-RPC tools for simulator setup, observation, UI actions, smoke checks, exploration, evidence capture, reporting, app-map memory, flow generation, suite generation, and automation output.

The goal is deterministic feedback from a usage perspective. Teams can detect product and flow issues before release, with artifacts that make each agent run auditable, inspectable, and repeatable.

Core capabilities

Built around simulator QA execution loops.

Simulator control

Prepare Android Emulator or iOS Simulator targets, launch apps, capture snapshots, and execute UI actions.

Evidence first

Collect screenshots, logs, dumps, reports, and local artifacts that explain what the agent observed.

Durable app map

Persist screens, features, flows, coverage context, issues, and generated test cases under the tested project.

Reusable outputs

Convert exploration into flows, test cases, suites, and generated automation for future runs.

Integrations

Connect Swipium to the agent environment you already use.

Swipium works through MCP, so it can support all models available in the connected agent client. Use it with Claude Code, Gemini, Codex, Grok, Grok Build, or any MCP-compatible workflow that can launch a local server.

Claude Code

Use Claude Code with Opus 4.8, Sonnet, 5.5, and any model exposed by the client. Project-scoped setup keeps QA tools tied to the mobile repository.

npm install -g swipium
swipium init claude --apply --scope project

Gemini

Connect Gemini to Swipium so simulator checks, evidence capture, and reports run locally through MCP.

npm install -g swipium
swipium init gemini --apply

Codex

npm install -g swipium
swipium init codex --apply

Grok and Grok Build

Use Grok or Grok Build through MCP-compatible clients or bridges to route simulator QA tasks into Swipium.

npx -y swipium verify
npx -y swipium

View integration details

Public v1 scope

Local, simulator-first, explicit where risk exists.

Android Emulator and iOS Simulator support.
Local MCP stdio server for agent clients.
Local evidence artifacts and app-map memory.
Consent gates for mutating actions.
Secret redaction for credentials, tokens, OTPs, and generated sensitive values.
Node.js 20 or newer.

Documentation

Start with the autopilot tool, then inspect the evidence.

Open docs on GitHub

Install or run

npx -y swipium verify
npm install -g swipium

Configure an MCP client

{
  "mcpServers": {
    "swipium": {
      "command": "npx",
      "args": ["-y", "swipium"],
      "cwd": "/absolute/path/to/mobile-app"
    }
  }
}

Ask an agent

Test this app with Swipium.
Start with qa_test_this.
Generate a report with evidence.

Blog

May 31, 2026

Introducing Swipium 1.0.0

A free and open-source MCP project for simulator-based mobile QA agents.

Read the launch post