Is TabRunner MCP server safe?

Yes, with the usual care.

A86/100grade A

Passed every safety check we run. Maintained, authenticated, reachable, clean scan.

No critical or high findings in the latest scan.

How TabRunner compares

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

Safety score: 86/100; higher than 67% of 807 Scraping and browsing servers
Tools that change things: 13%; typical: 0%. Fewer write tools means less an agent can break

What its tools let an agent do: 18 read · 1 create · 2 change · 2 run or deploy

scanner v0.1.10 · 2026-10-24 · same rubric, same numbers if you re-run it

1 medium

Code scan2 source files scanned20/25
–Live reliabilityno gateway calls yet and no remote to proben/a
–Tool poisoningtools not inspected (local package is not executed); not countedn/a
Auth qualitylocal package, no credentials required12/15
Maintenancelast push 1 days ago15/15
Maintainer identityregistry namespace matches repository owner; website matches verified namespace9/10

mediumeval / new Function usedexec.eval

dist/tabrunner-mcp.js: …eCode, sch); const makeValidate = new Function(`${names_1.default.self}`, `${names_1.de…

Overall 86/100. Components that don't apply are left out of the denominator. Any critical finding is an F.Rubric Appeal a finding JSON

Tap
Browser MCP for logged-in tasks. Uses your Chrome — credentials stay local. Zero-token replay.
not reviewed
Growing
B
Agentic Browser
Give any AI agent your real Chrome: text perception, visible cursor, ~4x fewer tokens.
not reviewed
Growing
B
Unbrowse
Websites as APIs: read pages, run site tasks via learned APIs, cloud browser with saved logins.
not reviewed
Established
A