e2e
OfficialServer Configuration
Describes the environment variables required to run the server.
| Name | Required | Description | Default |
|---|---|---|---|
| E2E_TELEMETRY_DISABLED | No | Set to 1 to opt out of anonymous CLI telemetry. |
Instructions
Guidance the server publishes about itself, which clients place ahead of the tool catalog so the model reads it before choosing anything.
e2e is a local-first end-to-end test runner; this server drives an e2e project's app (its e2e.config.ts) live. Call open_session (optionally with a target, a config path, and headed: true when the user wants to watch) to get a session, its tool catalog, and the first observation. A project with no e2e config file still opens one: pass engine, the engine package to drive ({engine: "@e2e-dev/web", app: {url: "http://localhost:3000"}}; {engine: {package: "@e2e-dev/mobile", options: {platform: "ios"}}, app: {bundleId: ""}}). Then call {tool, args} runs any catalog tool: observe, the grammar its engine honors (each action answers with the test line that repeats it), type_secret, locate, run_code (runs the test statements you are about to write), test_lines (those lines and the statements run_code passed, in order, as a draft test body), screenshot, start_recording and stop_recording when the engine records video (a video of the app for a pull request), and the project's own tools; tools lists them, tools {tool} shows one tool's arguments. close_session when done. Several sessions can be open at once, each with its own browser or device, so parallel agents (subagents) each open their own: pass the session id from open_session to every tools, call, and close_session. Before you write or edit a test, read the writing-tests guide: the resource e2e://guide/writing-tests, or npx e2e guide writing-tests in a shell. Write the test (tests/*.e2e.ts) while you walk the flow, adding each step to the file as you take it, and run it with run_tests {files: ["tests/x.e2e.ts"]} (the same run as npx e2e run ); run_tests without files runs the whole suite. To fix a failing test, open_session {test: "tests/x.e2e.ts:12"} runs it in a session and stops on the screen where it failed. Resources e2e://guide and e2e://guide/{topic} hold the writing guide.
Capabilities
Features and capabilities supported by this server
Protocol revision2025-11-25
| Capability | Details |
|---|---|
| tools | {
"listChanged": true
} |
| logging | {} |
| resources | {
"listChanged": true
} |
Tools
Functions exposed to the LLM to take actions
| Name | Description |
|---|---|
| open_sessionA | Open a live session on one target of an e2e project: loads the config, starts the app command the target declares (if any), boots the engine (a browser, a simulator), opens the app (its URL, or the pinned app on a device), and returns the session id, the catalog of tools it can run, and the first observation. Where the project has no e2e config file, pass engine to open a session on that engine: {engine: "@e2e-dev/web", app: {url: "http://localhost:3000"}}. With test, it runs that one test first and stops on the screen where the test passed or failed, with the failure and its line ahead of the catalog. Several sessions can be open at once, one per agent, each with its own engine: pass the returned session id to every later call. Then act with call and look with call {tool: "observe"}. |
| toolsA | List the tools a session can run through call: observe, the grammar its engine honors (one tool per action the engine declares, type_secret when a secret is configured, and screenshot and the point tools), locate, run_code (test statements run on the live app), test_lines (the test line each action printed and the statements run_code passed, as a draft test body), start_recording and stop_recording when the engine records video, and the project's own tools. With tool, shows that tool's full description and the JSON Schema of its arguments. |
| callA | Run one tool of a session by name, with its arguments as an object: call {tool: "tap", args: {target: "n42"}, session: ""}. The session's catalog (from open_session or tools) names the tools and their arguments. Actions report what changed on screen and the test line that repeats them; node ids are valid only for the newest observation. |
| close_sessionA | Close a live session: save a recording still running, end the attempt, dispose the engine, and stop the app processes the session started. |
| run_testsA | Run tests as npx e2e run does and return what it printed: each test, the failures with their code frames, and the summary. Without files it runs every test the config discovers; files narrows to a test file, a directory, a glob, or one test (tests/checkout.e2e.ts:12). The run is the CLI's own, in its own process, with its workers, retries, replay cache, and report (.e2e/report.json by default); it needs no open session and leaves open sessions alone. One run at a time; cancelling the call interrupts it as Ctrl-C would. To fix a failing test, open_session {test: ":"} stops on the screen where it failed. |
Prompts
Interactive templates invoked by user choice
| Name | Description |
|---|---|
No prompts | |
Resources
Contextual data attached and managed by the client
| Name | Description |
|---|---|
| guide | How to set up e2e, write tests, use agent steps, run the CLI, and read a failing run |
| agent | One topic of the guide: agent, bug-bash, debugging, explore, mcp, running, setup, writing-tests |
| bug-bash | One topic of the guide: agent, bug-bash, debugging, explore, mcp, running, setup, writing-tests |
| debugging | One topic of the guide: agent, bug-bash, debugging, explore, mcp, running, setup, writing-tests |
| explore | One topic of the guide: agent, bug-bash, debugging, explore, mcp, running, setup, writing-tests |
| mcp | One topic of the guide: agent, bug-bash, debugging, explore, mcp, running, setup, writing-tests |
| running | One topic of the guide: agent, bug-bash, debugging, explore, mcp, running, setup, writing-tests |
| setup | One topic of the guide: agent, bug-bash, debugging, explore, mcp, running, setup, writing-tests |
| writing-tests | One topic of the guide: agent, bug-bash, debugging, explore, mcp, running, setup, writing-tests |
TDQS
Scored across 5 tools
Each tool has a distinct primary role: open/close a session, run tests, list session tools, or dispatch one session tool call. There is some overlap between run_tests and open_session with a test argument, and between tools and call, but the descriptions make the boundaries clear.
Three tools follow a verb_noun pattern (open_session, close_session, run_tests), but tools is a bare noun and call is a bare verb. The set is readable and uses lowercase snake_case throughout, but the convention is not consistently applied.
Five tools is well-scoped for a meta-server that delegates most session actions through call. Each tool has a clear purpose and none feels redundant or excessive.
The surface covers the core e2e lifecycle: opening and closing sessions, running test suites, inspecting session tools, and executing them. Minor gaps include no explicit list_sessions or session status tool, though observation is available through call.