Smolanalytics

io.github.Arjun0606Published by GitHub account Arjun0606v0.92.1Updated Oct 24, 2026

End-to-end tests from one sentence: an agent drives a real browser, and passing runs replay free.

VerifiedSTDIODesktop onlyBrowser AutomationDeveloper Tools

Overview

AI-generated overview

Lets an assistant write and run end-to-end browser tests from plain-English sentences, with passing runs replayed without model calls.

What you can do
The server exposes three tools: run_tests, can_i_ship and list_tests. A test is a single sentence in a markdown file; an agent opens a real browser, reads the page through its accessibility tree, works out how to perform the described check, and returns one of five verdicts: passed, failed, stale, errored or flaky. A passing run is recorded, and later runs replay that recording with no model call until the recording stops fitting the app.
When to use it
Useful when you want end-to-end checks for a web app without writing or maintaining selector-based test code, and when you want an assistant to run a suite of sentence tests and report which ones broke. Suited to local or CI runs against a preview URL, including per-pull-request comments.
Requirements
Runs as a local process via npx or an OCI image, so Node.js or a container runtime is needed. Requires your own ANTHROPIC_API_KEY for a first run of a test that has no recording yet; replays need no key. Network access to the target site and to the model provider is required. The hosted service is a separate paid product.
Before you install
The ANTHROPIC_API_KEY secret is used by the local runner, and first runs of tests consume paid model usage roughly comparable to an agent conversation. The server drives a real browser against the URL you give it, so point it at sites you are authorized to test. It is commercial software, not open source, and the hosted side is billed monthly after a trial.

Installation

In SourceWeft

  1. Open Smolanalytics in the dashboard and add it to a workspace.
  2. Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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 · The nightly proof · Docs · npm

sh
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.

On every pull request

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.

In your editor (MCP)

json
{ "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.

Evidence rather than claims

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.

What it costs

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.

Source: README.md at commit 38bc278

Tools

0
SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

1
  1. v0.92.1LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

  • Reached in the last 30 days25 pts

    Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.

  • Auth declared10 pts

    Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.

  • Tools listed15 pts

    Answer tools/list without a credential, or ship a package that starts in a sandbox without one.

  • DescriptionRequired15 pts
  • Logo10 pts
  • Documentation15 pts
  • License10 pts