Runs end-to-end tests for web, iOS, and Android apps where an agent follows natural-language steps, then replays verified steps without model calls. For developers and coding agents.
Use it now
Keep it with up to 9 other tools you're setting up, then share them all as one link.
Try this first
Ask your assistant, with e2e connected:
- Agent Steps
Use e2e to drive the app toward a natural-language goal: ‹what you need›
- Step Caching
Use e2e to replay recorded agent actions on later runs: ‹what you need›
- Exploratory Testing
Use e2e to explore an app from a goal: ‹what you're looking for›
Connect it over MCP
{
"mcpServers": {
"testerarmy-e2e": {
"command": "npx",
"args": [
"e2e",
"mcp"
]
}
}
}claude mcp add testerarmy-e2e -- npx e2e mcp
It runs on your computer, so web assistants such as Grok and ChatGPT can’t start it.
Setup guide: e2e.com/docs/quickstart
Install the CLI
Install it as its own instructions say.
Setup guide: e2e.com/docs/quickstart
Compare
Press Compare to add it to the tray at the bottom of the window, then pick up to 2 others anywhere on the site.
- Access
- CLIMCP
- Auth
- None
- Skills
- 5
Skills
Agent Steps
Drives the app toward a natural-language goal with agent.act and checks the outcome with agent.assert inside a normal test.
Step Caching
Replays recorded agent actions on later runs with no model calls, and lets the agent take over again when the app changes.
Exploratory Testing
Explores an app from a goal without a test file, planning and performing steps, then reports the bugs it finds.
Live App Session
Opens a live web, iOS, or Android session for a coding agent over MCP to act on the app, check locators, run tests, and record video.
Visual Comparison
Compares the whole screen or one element against a stored screenshot on web, iOS, and Android in the same test.
