MCP.Market

Smolanalytics MCP server

by Arjun0606·io.github.Arjun0606/smolanalytics·v0.92.1·4 stars

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

B83/100grade B
What users say
No reviews yet
Be the first
Safety scan
B83/100

full report

Adoption
Growing

4 stars56 downloads/wk

Reviews

Write one

Nobody has reviewed Smolanalytics yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

Smolanalytics tools (3, 2 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • can_i_shipwrite action

    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 reports the gaps rather than just the failures.

  • list_tests

    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.

  • run_testswrite action

    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' means this runner failed, not the app. Costs model calls when a recording is missing or stale.

Public scan report

scanner v0.1.10 · 2026-10-15 · same rubric, same numbers if you re-run it

no findings
  • Code scan38 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitystatic API keys via environment variables6/15
  • Maintenancelast push 21 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 83/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How Smolanalytics compares

Against every graded Scraping and browsing MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
83/100
higher than 60% of 866 Scraping and browsing servers
Tools
3
the typical Scraping and browsing server has 6
Tools that change things
67%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
4
more than 72% of 583 Scraping and browsing servers
Downloads a week
56
more than 38% of 309 Scraping and browsing servers with a package

What its tools let an agent do: 1 read · 1 change · 1 run or deploy

Install Smolanalytics in Claude Code, Cursor or VS Code

claude mcp add smolanalytics -- docker run -i --rm ghcr.io/arjun0606/smolanalytics:v0.92.1
Add to Cursor

What the publisher says

From the Smolanalytics repository's README, as published. We do not edit it. Read it on GitHub

smolanalytics

Analytics that investigates your product for you. What changed, who it hit, what it cost, what shipped near it.

smolanalytics.com · Live demo · Docs

smolanalytics is commercial software. The hosted product at smolanalytics.com is the way to use it: a 14-day trial at Pro limits with no card, then from $19/mo, with each project running as its own isolated instance.

What it does, briefly:

daily; findings arrive ranked by cost (dollars when the metric carries revenue, people otherwise), each with the segment carrying it, the ship that correlates with it, and the next move. A quiet day says so and stops.

  • Investigates on its own. Every product event is tested for step changes

receipt on your desk. Regressions that return to baseline retire themselves as "recovered" — computed, never asserted.

  • Heals. Guardrailed experiments auto-revert when they breach, with the

dates every finding by the day it would first have surfaced.

  • Replays. backtest re-runs the investigator over your own history and

investigate, which returns the whole desk in one call, and markfindingacted, which closes the loop from your editor. Deterministic reports, never generated SQL.

  • Answers in your editor. 97 MCP tools over your own model — including

Questions: smolanalytics.com/contact

Nothing above is checked by us. What we check is on the safety report.

Smolanalytics: common questions

Is Smolanalytics MCP server safe?
Mostly: it is graded B (83/100). Read the Smolanalytics safety report
How do I install Smolanalytics?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does Smolanalytics need an API key?
Yes. The registry entry asks for ANTHROPIC_API_KEY.
Is Smolanalytics maintained?
The last commit was 41 days ago (2026-09-24). The latest release is v0.92.1.
What can I use instead of Smolanalytics?
Servers from other publishers that do the same job: GrowBlocks Dev Kit MCP server, Agent360 Browser MCP server and FableCut MCP server. Compare all Smolanalytics alternatives.
How does Smolanalytics compare with other Scraping and browsing MCP servers?
safety score 83/100 (higher than 60% of 866 Scraping and browsing servers); tools 3 (the typical Scraping and browsing server has 6); tools that change things 67% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to Smolanalytics

Same job from other publishers: the closest match first, then the best rated.

All Smolanalytics alternatives →
  • GrowBlocks Dev Kit
    Build, play-test with screenshots, and ship three.js browser games on GrowBlocks.
    A
  • Agent360 Browser MCP
    Drive your real, logged-in Chrome from any AI agent - 40 tools. Needs our Chrome extension too.
    A
  • FableCut
    Zero-dependency browser video editor AI agents drive via a JSON timeline over MCP; ffmpeg export.
    A
  • Tap
    Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
    B
  • Dejo
    A browser your AI agent remembers. Learn a site once, replay it in one call, zero model calls.
    A