LegitShow is the trusted source on every newly launched software product: what it does, who it’s for, how it actually holds up, and whether the AI engines are already reading it. Built to be what AI cites.

Web apps, SaaS, AI tools, MCP servers and developer tools. How we measure →


Legit.Show benchmarks every launched service it lists — measured deterministically from the public surface. See the methodology →

Cross-links · Directory · Reports · Insights · What AI reads · Methodology · About

Privacy · Terms · @Legit_Show on X · GitHub · operated by Madeflo Inc., a Delaware corporation. Benchmark engine powered by commit.show.

MCP & Integrations

turbo-browser-mcp

Source: Tthanh2k6/turbo-browser-mcp

Last updated 2026-11-15 · benchmark measured 2026-11-15 — deterministic & reproducible

turbo-browser-mcp: a browser automation tool built as an MCP server.

turbo-browser-mcp at a glance

turbo-browser-mcp is an open-source MCP (Model Context Protocol) server that lets AI coding agents control a web browser, built on Playwright, for developers and browser automation engineers.

Good for

  • Letting an AI agent fill out and interact with web forms (including React inputs, comboboxes, rich-text editors, and file uploads) in a single call
  • Reducing the number of model turns and page text an agent has to process by batching multiple browser actions together
  • Automating browser tasks while keeping a human in control of final 'Submit/Send/Pay/Confirm' actions, which are blocked by default

Questions people ask

What does turbo-browser-mcp do?
It is an MCP server for browser automation, built on Playwright, that gives an AI agent 11 tools for tasks like filling forms, batching actions, and reading page content, each designed to do more per call than typical one-action tools.

Does turbo-browser-mcp hide that a browser is being automated, or solve CAPTCHAs?
No. The server does not use stealth patches, fingerprint changes, or CAPTCHA solving; if a site has a bot check, it can hand control of the tab to a person and continue afterward using the wait_for_human feature.

What happens when a form is ready to submit?
Buttons that look like a final commit action (Submit, Send, Publish, Pay, Confirm, and equivalents in Korean, Japanese, Chinese, and Vietnamese) are blocked by default so a person can take the last click, though this can be turned off with allowSubmit:true or the --allow-submit flag.

What do I need to install and run turbo-browser-mcp?
You need Node 20 or newer and a Chromium-based browser such as Chrome, Edge, Brave, or Playwright's Chromium; it can be added to Claude Code or configured in any client that reads an mcpServers JSON config, such as Cursor, Claude Desktop, or Antigravity.

Is turbo-browser-mcp free to use?
The material does not state a price for turbo-browser-mcp itself; it is distributed under the MIT license on GitHub and npm.

Written by Legit.Show from github.com on 2026-11-17. It does not change the score.

67/100
3/7 frames
Legit Benchmark — the simple average of 3 measured frames. Frames we could not measure are left out of the average, never counted as zero. Every frame is shown below with its evidence.
Checked 2026-11-15 · scores move as sites change

Are you the maker of turbo-browser-mcp? Claim this listing. It is free, takes a meta tag, a DNS record or GitHub admin rights, and never changes the score.

Launched something? Add your product, free.

To cite this score: legit.show/s/gh-turbo-browser-mcp/2026-11-15. That address never changes; this page moves with every re-measure.

Legit.Show scored turbo-browser-mcp 67/100 on 2026-11-15, measured across 3 of 7 frames from its public surface. legit.show/s/gh-turbo-browser-mcp/2026-11-15

Is turbo-browser-mcp production-ready?

Legit.Show scores turbo-browser-mcp 67 out of 100 — the simple average of its 3 measured frames. Legit.Show ran its deterministic 7-Frame production-readiness benchmark on turbo-browser-mcp (github assessment), measured from the public surface with no LLM in the scoring path. Its strongest frame is Security; its weakest is Discoverability. 3 of the seven frames returned a score; Performance, Accessibility, Privacy and Reliability were not measurable on this service and are recorded as null — not as zero. Maintenance is an additional frame from the open-source teardown, scored separately from the seven. Every frame it averages is published with its evidence on the Legit.Show listing.

The 7 Frames

Open-source teardown

Scored separately — not one of the seven.

What we measured

Who it's for

Developers · MCP users · Browser automation engineers

Sources and updates

Description
Taken from github.com's own website on 2026-11-15.
Code
github.com/Tthanh2k6/turbo-browser-mcp.
Benchmark
Measured by Legit.Show from the live site, the way any visitor sees it — with no access to its code or accounts. Same method for every product, and no AI decides the score. Last checked 2026-11-15.

Put together from public information, without turbo-browser-mcp's involvement. If anything here is wrong, tell us and a person will check it.

Visit turbo-browser-mcp → · Alternatives to turbo-browser-mcp → · How this was measured →

See how turbo-browser-mcp ranks among tested ai browser automation products →

Other tested ai browser automation products