smolanalytics

MCPcommunity
v0.21.0Arjun VarmaSEE LICENSE IN LICENSEUpdated todaynpmGitHub

End-to-end tests without test code. Write one sentence, an agent drives a real browser and returns a verdict, and a passing run is recorded so the next one calls no model. Runs on any URL with no account.

Works in
ClaudeCursorCopilotGemini

Inferred from the transports this listing declares (stdio). A client not listed here hasn’t been ruled out — it just isn’t something Forge can confirm.

Automatically indexed from public sources. Not yet verified by the developer on Forge.Claim this listing →
719Downloads/wk
3GitHub stars
1Forks
todayLast update
Reads these credentials
  • ANTHROPIC_API_KEYAPI keyoptional

    Your own Claude key. run_tests needs it for a test with no recording yet; a replay needs none.

Declared by the author in the official MCP registry. Forge does not store, broker, or ever see these values — the config below is scaffolded with placeholders you fill in locally.

Package
AuthorArjun Varma
LicenseSEE LICENSE IN LICENSE
Version0.21.0
Sourcenpm+mcp-registry
Trust Status
B
60/100Good
Listed in Forge index+10/10
Publisher identity verified+0/20
Publisher: run `forge publish` from the package repo to claim ownership
Ed25519 publish signature+0/5
Included automatically when the publisher runs `forge publish`
Domain verification+0/5
Publisher: host /.well-known/forge.json on the package homepage with { "publisher": "<github-login>" }
npm Trusted Publishing (Sigstore)+0/5
Publish from GitHub Actions with --provenance so the attestation binds this package to this repo
npm maintainer match+0/5
Earned once your identity is verified above and that login is an npm maintainer of this package
CVE scan · clean+30/30
Static analysis · clean+20/20
Paste into Claude Code, Cursor, or any AI assistant to fix all gaps
StatusCommunity-indexed
PublisherUnverified
SignatureUnsigned
Domain
Provenance
Dependencies✓ 0 resolved · none vulnerable
Tool surface11 tools · 1 privileged
Security scan✓ Cleanv0.21.0 · todayHow well does this scan work?
EvalsNone
IndexedSep 9, 2026

Verification confirms publisher identity (repo ownership), not code safety. The security scan covers known CVEs and suspicious install scripts.

Tools

11 tools · 1 privileged
Statically extracted from the published packagev0.21.0 · 1h ago

Read out of the source npm actually ships, at scan time. The package was never executed. Tools registered dynamically at runtime, or hidden inside bundled or minified code, can be missed — so this is a floor on the tool surface, not a complete census of it.

run_testsRun the end-to-end suite against a URL and return the verdict for every test. Use this after changing the app to find out whether a user flow still works. Returns passed/failed/stale/errored/flaky per test — 'stale' means a recording stopped fitting and the flow was NOT verified, and 'errored' mean…

Run the end-to-end suite against a URL and return the verdict for every test. Use this after changing the app to find out whether a user flow still works. Returns passed/failed/stale/errored/flaky per test — 'stale' means a recording stopped fitting and the flow was NOT verified, and 'errored' mean…

No input schema was published for this tool.

can_i_shipRun the suite and answer whether it is safe to ship, INCLUDING what was not checked — flows whose recordings went stale, tests that were flaky and therefore prove nothing, tests skipped by --since, and runs that errored on our side. Use this before merging or releasing. This is the only tool that r…

Run the suite and answer whether it is safe to ship, INCLUDING what was not checked — flows whose recordings went stale, tests that were flaky and therefore prove nothing, tests skipped by --since, and runs that errored on our side. Use this before merging or releasing. This is the only tool that r…

No input schema was published for this tool.

list_testsList the tests that exist, with the plain-English sentence each one checks and whether it has a recording. Use this to find out what is already covered before writing a new test, or to tell the user what this project verifies.

List the tests that exist, with the plain-English sentence each one checks and whether it has a recording. Use this to find out what is already covered before writing a new test, or to tell the user what this project verifies.

No input schema was published for this tool.

proposePropose the end-to-end tests this application is worth writing, most important first.

Propose the end-to-end tests this application is worth writing, most important first.

No input schema was published for this tool.

clickClick one element from the ELEMENTS list.

Click one element from the ELEMENTS list.

No input schema was published for this tool.

fillType text into a textbox, searchbox or combobox. Replaces what is there.

Type text into a textbox, searchbox or combobox. Replaces what is there.

No input schema was published for this tool.

pressPress a key, e.g. Enter. Use when a form submits on Enter.

Press a key, e.g. Enter. Use when a form submits on Enter.

No input schema was published for this tool.

gotoNavigate to a URL. Prefer clicking; use this only when the test says to open a page.

Navigate to a URL. Prefer clicking; use this only when the test says to open a page.

No input schema was published for this tool.

scrollScroll when what you need is probably above or below the fold.

Scroll when what you need is probably above or below the fold.

No input schema was published for this tool.

finishEnd the test. passed=true only if you directly OBSERVED what the test asked you to verify.

End the test. passed=true only if you directly OBSERVED what the test asked you to verify.

No input schema was published for this tool.

uploadprivilegedAttach a file to a file-upload control — either a file input, or a button that opens a file picker.

Attach a file to a file-upload control — either a file input, or a button that opens a file picker.

No input schema was published for this tool.

11 of 11 tools published a description.

Tool names and descriptions are written by the publisher and shown verbatim as inert text. They are the strings an MCP client passes to a model, so Forge scans them for prompt-injection patterns — any finding appears with the security scan above. “Privileged” is a keyword match on the tool name, not an audit of what the tool does: a benign-sounding name can still do anything.

About

End-to-end tests without test code. Write one sentence, an agent drives a real browser and returns a verdict, and a passing run is recorded so the next one calls no model. Runs on any URL with no account.

Keywords
e2e-testingend-to-end-testingtestingtest-automationplaywrightqaai-testingagentic-testingbrowser-testingregression-testingno-code-testingcigithub-actionspull-requestmcpcursorclaudevibe-coding
Alternatives
Comparing tool surfaces…

Dependency tree

What one Forge scan resolved from npm metadata on 2026-09-09 — observed resolution, not a publisher declaration.

0 packages resolved · 0 direct · none carrying advisories Resolution stops at depth 4 and 60 packages.

This package declares no runtime dependencies.

Topics

Related in browser automation & scraping