Executes multi-step iOS and Android mobile UI workflows in a single agent tool call using accessibility controls.
Also known as huaaudio/jevsim, @huaaudio/jevsim
- Stars
- 0
- Tools
- —
- Downloads, 30 days
- 149
- Latest version
- 0.1.0
- Last commit
- Sep 21, 2026
- License
- MIT
What is JevSim MCP?
JevSim executes multi-step iOS and Android mobile UI workflows in a single agent tool call using accessibility controls.
Summary generated from the project's README
About JevSim MCP server
Automating multi-step mobile UI sequences in a single tool call is what JevSim enables for developers working on iOS and Android applications. Instead of an agent returning to its main reasoning loop after every single tap or text entry, this local MCP server allows an agent to delegate an entire plan—such as navigating menus, entering data, and verifying results—to a single execution command. This approach significantly reduces execution time by minimizing the round trips between the agent and the tool.
To use JevSim, you must configure an MCP client to run the package via npx and provide a TYPESAFE_API_KEY for the Jev text-based selection model. The server connects to an iOS backend using XcodeBuildMCP on a macOS simulator, or an Android backend using Appium and UIAutomator2 via ADB. Users can manage workflows through three specific tools: jevsim_status for connectivity checks, jevsim_inspect for reading accessibility states, and jevsim_run_steps for executing up to ten sequential actions like tap, type, scroll, wait, and assert.
What you can do with it
- 1Automate repetitive mobile workflowsDevelopers can delegate known sequences like reproducing bugs or exercising forms to the server.
- 2Verify app state changesThe server can confirm that a specific UI element appears after a series of actions.
Written from the project's README. Every use case is checked against a quote from it.
How to install JevSim MCP
Formats verified 10 Nov 2026Add to CursorAdd to GooseInstall JevSim MCP in Claude Code
$ claude mcp add --env 'TYPESAFE_API_KEY=<YOUR_TYPESAFE_API_KEY>' jevsim -- npx -y @huaaudio/jevsimInstall JevSim MCP in Cursor
~/.cursor/mcp.json
{
"mcpServers": {
"jevsim": {
"command": "npx",
"args": [
"-y",
"@huaaudio/jevsim"
],
"env": {
"TYPESAFE_API_KEY": "<YOUR_TYPESAFE_API_KEY>"
}
}
}
}Install JevSim MCP in VS Code
.vscode/mcp.json
{
"servers": {
"jevsim": {
"type": "stdio",
"command": "npx",
"args": [
"-y",
"@huaaudio/jevsim"
],
"env": {
"TYPESAFE_API_KEY": "<YOUR_TYPESAFE_API_KEY>"
}
}
}
}Install JevSim MCP in VS Code CLI
$ code --add-mcp '{"name":"jevsim","type":"stdio","command":"npx","args":["-y","@huaaudio/jevsim"],"env":{"TYPESAFE_API_KEY":"<YOUR_TYPESAFE_API_KEY>"}}'Install JevSim MCP in Claude Desktop
claude_desktop_config.json
{
"mcpServers": {
"jevsim": {
"command": "npx",
"args": [
"-y",
"@huaaudio/jevsim"
],
"env": {
"TYPESAFE_API_KEY": "<YOUR_TYPESAFE_API_KEY>"
}
}
}
}Install JevSim MCP in Codex
$ codex mcp add jevsim --env 'TYPESAFE_API_KEY=<YOUR_TYPESAFE_API_KEY>' -- npx -y @huaaudio/jevsimInstall JevSim MCP in Codex config.toml
~/.codex/config.toml
[mcp_servers.jevsim] command = "npx" args = ["-y", "@huaaudio/jevsim"] [mcp_servers.jevsim.env] TYPESAFE_API_KEY = "<YOUR_TYPESAFE_API_KEY>"
Install JevSim MCP in Gemini CLI
$ gemini mcp add -s user -e 'TYPESAFE_API_KEY=<YOUR_TYPESAFE_API_KEY>' jevsim npx -- -y @huaaudio/jevsimInstall JevSim MCP in Gemini settings.json
~/.gemini/settings.json
{
"mcpServers": {
"jevsim": {
"command": "npx",
"args": [
"-y",
"@huaaudio/jevsim"
],
"env": {
"TYPESAFE_API_KEY": "<YOUR_TYPESAFE_API_KEY>"
}
}
}
}Configuration
TYPESAFE_API_KEYSecretTypeSafe API key for semantic selection. Exact-identifier workflows need no key.
JEVSIM_ADB_COMMANDAndroid only: adb executable. Use an absolute path if needed.
JEVSIM_ANDROID_APPIUM_URLAndroid only: separately running Appium 3/UIAutomator2 server on loopback.
JEVSIM_MODELTypeSafe selection model.
JEVSIM_XCODE_ARGSiOS only: JSON array of XcodeBuildMCP arguments.
JEVSIM_XCODE_COMMANDiOS only: XcodeBuildMCP executable. Use an absolute path if needed.
| Name | Description | |
|---|---|---|
| TYPESAFE_API_KEY | TypeSafe API key for semantic selection. Exact-identifier workflows need no key. | Secret |
| JEVSIM_ADB_COMMAND | Android only: adb executable. Use an absolute path if needed. | |
| JEVSIM_ANDROID_APPIUM_URL | Android only: separately running Appium 3/UIAutomator2 server on loopback. | |
| JEVSIM_MODEL | TypeSafe selection model. | |
| JEVSIM_XCODE_ARGS | iOS only: JSON array of XcodeBuildMCP arguments. | |
| JEVSIM_XCODE_COMMAND | iOS only: XcodeBuildMCP executable. Use an absolute path if needed. |
Automated checks
Ran Nov 14, 2026Full report →Passed our automated checks. That is not a security audit: read the code and give the server the narrowest access it needs. How checks work
- Source repository linked and reachablehuaaudio/jevsim is public and reachablegithub.com/huaaudio/jevsim ↗Pass
- Package names this repository as its source@huaaudio/jevsim names huaaudio/jevsim as sourcenpmjs.com/package/@huaaudio/jevsim ↗Pass
- Build provenance (Sigstore attestation)No build attestation published for this releaseNot checked
- Open source license (OSI)MITspdx.org/licenses/MIT.html ↗Pass
- Commit or release in the last yearLast commit or release 2026-09-21github.com/huaaudio/jevsim ↗Pass
- OpenSSF ScorecardNot checked
- Package name not close to a popular packageNo popular package one edit away from @huaaudio/jevsimPass
- No critical advisory in the package or its dependencies107 resolved dependencies checked; no critical advisoryosv.dev ↗Pass
- No hidden instructions to the model0 tool descriptions and the README read; no override phrases, credential paths or hidden charactersPass
- Destructive tools are labelledNot checked
- Remote endpoint answers the MCP handshakeNot checked
README
View on GitHubJevSim
Complete a mobile UI sequence in one agent tool call.
JevSim is a local MCP server for agents working with iOS and Android apps. Give it a short plan—navigate, enter text, save, verify—and it executes the steps without returning to your main reasoning loop after every interaction. Jev, a text-based selection model, matches descriptions to current accessibility controls. XcodeBuildMCP (iOS) or Appium/UIAutomator2 (Android) performs the actions and checks the results.
If you are a human, give your agent this repository URL and ask: “Install JevSim for my iOS/Android project, connect it to your MCP tools, and verify the setup.” The instructions below are for that agent.
Speed comparison
We reran the same ten-tap iOS Settings tour with the same checks after every action: open five sections and return from each. Pure agent means the main agent reads each screen and chooses the next control through XcodeBuildMCP. Agent + JevSim means it delegates the full route in one jevsim_run_steps call, with Jev selecting all ten targets.
| Approach | Median execution time | Verified runs | Speedup |
|---|---|---|---|
| Pure agent + XcodeBuildMCP | 117.3 s | 3/3 | 1× |
| Agent + JevSim + XcodeBuildMCP | 35.7 s | 3/3 | 3.3× |
Measured September 21, 2026: GPT-6-astra (high reasoning) in Codex, Jev 1.13.0, XcodeBuildMCP 2.7.0, iPhone 17e / iOS 26.5 Simulator. Times include observations, target decisions, actions, checks, and intermediate agent/tool round trips; setup and initial route planning are excluded. This is one navigation benchmark with three runs per approach, not a general debugging or Android speed guarantee. Run details and reproduction.
Agent installation
- Inspect the environment. Use Node.js 24 and npm. Choose the platform from the user's project; install only that backend. Reuse existing tools and credentials where available.
- Use the npm package. Configure the MCP client to run
npx -y --package=@huaaudio/jevsim@0.1.0 jevsim. This downloads the compiled package; no clone or build is needed. Use an absolute path to Node.js 24’snpxif the client has a restricted PATH. Source installation remains available for development. - Prepare the backend. For iOS, use macOS, Xcode, and a booted simulator; JevSim starts its own pinned XcodeBuildMCP process. For Android, prepare ADB and a device/emulator, then start local Appium with UIAutomator2 using the Android instructions. Build, install, and launch the user's app with your existing tools.
- Configure Jev. Supply
TYPESAFE_API_KEYthrough your client's secret/environment configuration. The npm launcher does not automatically read.env; use the env-file launch option if needed. Preserve an existing.env; use .env.example only as a template. Never print or commit the key. Exact-identifier workflows also work without a key. - Register and verify the MCP server. Follow the agent installation runbook for absolute launch paths, client configuration, and readiness checks. Preserve other MCP servers. Installation is complete when you can discover all three tools, connect to the chosen backend, and inspect the intended device. Report any missing prerequisite precisely.
Delegate a workflow
| Tool | Use it to |
|---|---|
jevsim_status |
Check backend connectivity, credential presence, and device inventory |
jevsim_inspect |
Read the current accessibility state of one explicit device |
jevsim_run_steps |
Execute 1–10 supplied steps within 60 seconds; receive outcomes, timings, and any stop reason |
Call status and inspect first. For iOS, pass the observed simulatorId; for Android, pass platform: "android" and the ADB deviceId. Derive the plan from the app and the user's task. Every step must include a backend-verifiable expect condition.
For example, this is one step only if your app exposes the stated destination identifier:
{
"action": "tap",
"target": { "description": "Open the profile editor" },
"expect": { "predicate": "exists", "identifier": "profile.name" }
}
Use a unique observed target.identifier when available; it skips the model request. Otherwise, Jev selects among current action-compatible controls or abstains. It cannot invent steps or generate typing text. Supported actions are tap, type, scroll, wait, and assert. See the request schema and complete example.
Reserve the device until the call returns. A completed result means every supplied expectation matched. If execution stops, inspect completedSteps, reason, and actionStatus, then inspect the app and re-plan. Never blindly replay a workflow or an uncertain action. See agent usage and recovery.
When to use it
Delegate known sequences: reproduce a bug, navigate to a screen, exercise a form, or verify a change. Keep builds, code edits, visual interpretation, and decisions that depend on new information in your main agent. Split longer work into bounded sequences.
- Supported: iOS Simulator and native Android accessibility. Android has been live-tested on an Android 15 emulator on macOS; physical Android devices and Windows/Linux hosts remain unvalidated.
- Input: Android supports Unicode and empty replacement. The tested iOS backend accepts nonempty printable ASCII only.
- Limits: inaccessible controls, Android WebViews, and arbitrary desktop GUIs need other tools. JevSim does not interpret screenshots.
- Data: semantic selection sends accessibility text and field values to TypeSafe. Exact-identifier workflows skip those requests. Tool transcripts and backend logs may contain app data; see data handling.
Reference
Agent installation · Agent usage · Tools · Configuration · Troubleshooting · Release notes
Contributors: development guide for fixtures, tests, benchmark reproduction, and implementation history.
MIT. Independent project; automation backends and the TypeSafe service have their own terms and licenses.
JevSim MCP questions
How do I add JevSim MCP to Claude Code?
Run claude mcp add --env 'TYPESAFE_API_KEY=<YOUR_TYPESAFE_API_KEY>' jevsim -- npx -y @huaaudio/jevsim in your terminal. Add --scope user to make it available in every project.
How do I add JevSim MCP to Cursor?
Open ~/.cursor/mcp.json and add the server under mcpServers, using the Cursor config shown in the install section above.
How much faster is JevSim compared to a pure agent approach?
JevSim can provide up to a 3.3x speedup by delegating full routes in one call rather than returning to the main reasoning loop after every interaction.
What mobile platforms are supported?
It supports iOS Simulators via XcodeBuildMCP and native Android accessibility via Appium/UIAutomator2.
Does JevSim interpret screenshots?
No, JevSim does not interpret screenshots; it relies on accessibility controls and text-based selection.
What actions can the tool perform?
The supported actions are tap, type, scroll, wait, and assert.