smolanalytics
End-to-end tests written as one English sentence. An agent runs them in a real browser, and a passing run replays with no model call.
smolanalytics.com · · ·
接入你的智能体
發布者自己的指令。不是 PlugMCP 端點。
用我們的金鑰與日誌託管一份副本。
docker run -i --rm ghcr.io/arjun0606/smolanalytics:v0.92.1Claude Code 沒有本機指令的安裝連結。複製下方指令並在終端機中執行。
claude mcp add arjun0606-smolanalytics -- docker run -i --rm ghcr.io/arjun0606/smolanalytics:v0.92.1在終端機中執行。
{ "mcpServers": { "arjun0606-smolanalytics": { "command": "docker", "args": [ "run", "-i", "--rm", "ghcr.io/arjun0606/smolanalytics:v0.92.1" ] } }}claude_desktop_config.json
遠端 URL 還是本機指令? 兩種安裝方式的差異
來自發布者
End-to-end tests written as one English sentence. An agent runs them in a real browser, and a passing run replays with no model call.
smolanalytics.com · · ·
End-to-end tests without test code. Write one sentence, an agent drives a real browser on every pull request and tells you what broke. A passing run is recorded and replays with no model call. Commercial, hosted at smolanalytics.com.
npx smolanalytics test --url https://yourapp.com --test "the pricing page shows a monthly price"
A test is one sentence in a markdown file. An agent opens a real browser, reads the page through its accessibility tree, works out how to do what the sentence says, and returns a verdict. There is no test code, so there is no selector to update when a button moves.
A run that passes is recorded, and every run after it replays that recording with no model call at all. The agent comes back only when the recording stops fitting your app.
Five verdicts, never blurred: passed, failed, stale, errored, flaky. Only failed is a claim about your app. A recording that stopped fitting is stale, never a bug report, and a runner that could not finish is errored, never counted against you.
test --suite tests/ --url <preview> --comment runs a folder of sentences and leaves one comment on
the pull request, edited in place on every push: what broke, the file most likely responsible and
the evidence for that guess. Exit codes are 0 (clean), 1 (your app failed a test) and 2 (the runner
could not finish). The workflow file is in the docs.
{ "mcpServers": { "smolanalytics": { "command": "npx", "args": ["-y", "smolanalytics", "mcp"] } } }
Three tools: run_tests, can_i_ship and list_tests. Listed on the official MCP Registry as
io.github.Arjun0606/smolanalytics.
smolanalytics.com/proof is a GitHub Action that runs this product's own suite against two live sites every night and publishes every verdict, including the red ones. Nothing on that page is written by hand.
The CLI runs on your machine or your CI runner, on your own ANTHROPIC_API_KEY. A first run of a
test costs roughly what one agent conversation costs; a replay costs nothing. The hosted side at
smolanalytics.com is $19/month with 100 tested pull requests included,
after a 14-day trial with no card. This is commercial software, not open source.
Full CLI reference: cli/README.md. Questions: smolanalytics.com/contact.
End-to-end tests without test code. Write one sentence, an agent drives a real browser on every pull request and tells you what broke. A passing run is recorded and replays with no model call. Commerc
{ "mcpServers": { "arjun0606-smolanalytics": { "command": "docker", "args": [ "run", "-i", "--rm", "ghcr.io/arjun0606/smolanalytics:v0.92.1" ] } }}總覽
End-to-end tests without test code. Write one sentence, an agent drives a real browser on every pull request and tells you what broke. A passing run is recorded and replays with no model call. Commercial, hosted at smolanalytics.com.
工具
尚無工具清單。遠端伺服器會在首次健康檢查後取得工具清單。
常見問題
在本頁複製適用於 Cursor、Claude Desktop、Claude Code 或 VS Code 的 stdio 設定。它使用發布者的安裝方式,而不是 PlugMCP 代理伺服器。
發布者列出了以下環境變數:ANTHROPIC_API_KEY。
Smolanalytics 透過 stdio 在本機執行。
上次檢查時間:2026-10-28。 End-to-end tests without test code. Write one sentence, an agent drives a real browser on every pull request and tells you what broke. A passing run is recorded and replays with no model call. Commercial, hosted at smolanalytics.com.