Reflex

A browser built for your AI agent

Research products, fill forms, compare prices, scrape tables. All in plain English, in your own Chrome.

25 free calls the moment you install. No signup, no card.

Reflex MCP is a local MCP server that drives your own Chrome from any MCP client. It batches actions and returns compressed page views. In the July 22, 2026 agent run, individual tasks finished up to 2.2x faster end to end than Playwright MCP. Reflex never sends page content to our servers.

Already in Cursor, VS Code, or Claude Code? Add Reflex in one click.

How does Reflex MCP compare to Playwright MCP?

In the historical June 2026 tool benchmark, Reflex used 6 calls and ~13K estimated response tokens across three mutually verified flows versus 14 calls and ~56K for Playwright MCP, with 5 of 6 flows completed versus 3; some failures came from the benchmark runner. Tokens were estimated from characters. Current Playwright MCP supports form and script batching, and can return snapshot file links. Compare the dated results and workflow choices before choosing a tool.

Full Reflex vs Playwright MCP comparison · Benchmarks and methodology

	Playwright MCP	Reflex
Tool calls, 3 measured flows	14	6
Estimated response tokens, same flows	~56K	~13K
Flows completed, of 6 attempted	3	5
Full-page reader output: Wikipedia article	~31K estimated tokens	~4K estimated tokens
Full-page reader output: W3C CSS spec	~169K estimated tokens	~7K estimated tokens
Historical full-snapshot reread: unchanged page	~16K estimated tokens	91 characters: "(page unchanged)"

Historical June 2026 tool runs and page-reader sizes. Token estimates use characters divided by four. Some failed flows were benchmark-runner errors. See every number and how to reproduce it.

Page-reader rows compare full accessibility snapshots with Reflex views. Current Playwright MCP action responses can return short summaries and snapshot file links. These historical sizes do not describe every current tool call. The October 5, 2026 scripted comparison includes standard, batched, and tuned Playwright workflows on the benchmarks page.

Can I run multiple browsers in parallel?

Yes. Pass a session name on any Reflex tool call and it spins up a separate, isolated Chrome on demand, free. One agent can research ten sites at once; subagents can each drive their own browser. A shared Playwright MCP connection uses one browser; separate instances can also isolate parallel work. Reflex is the browser automation MCP built for parallel work from Claude Desktop, Cursor, and other MCP clients.

• flights
• hotels
• cars

one isolated Chrome each, running side by side

reflex_open(url, session: "flights")

Watch the token race.

Replay a measured flow →

Historical Wikipedia example: search an article, open its revision history

Playwright MCP5/5 calls

estimated reply tokens~30K

Reflex2/2 calls

estimated reply tokens~8K

Historical calls and estimated reply tokens from 2026-06-12. Token estimates are reply characters divided by four, excluding inputs, tool schemas, and model reasoning. Responses and timing are illustrated, not recorded payloads or a live benchmark. Across all three verified flows: 6 calls / ~13K tokens vs 14 calls / ~56K tokens (~2 calls per flow with Reflex).

Two minutes to your first task.

Built for agents, not just browsers.

Failures you can act on

When a step misses, Reflex sends back the closest matches, the console errors, and a screenshot, so your agent fixes it on the next try instead of guessing.

Checks built into the action

Reflex verifies the result inside the same call, so a task clearly succeeds or fails without an extra round trip to confirm.

0-token replay

Save a task and re-run it anytime with no AI and no tokens. It repairs itself when the page changes.

Your pages never leave your machine.

Reflex runs entirely on your computer: the MCP server, the browser, your logins, every page you visit. The only things that ever cross the network are your API key and a count of tool calls, so we can meter credits. We could not read your pages, sessions, or passwords if we wanted to; the architecture has no path for them.

Compare that to cloud browser products, where every page you visit renders on someone else's server.

Reflex servers

• Is this key valid?
• Credit balance
• Usage counts
• Paddle payments

No path exists for your pages, logins, or sessions to reach us.

API key + call countpages never cross

Your machine stays here

Claude Desktopor Cursor, Claude Code, any MCP client

Reflex MCP serverruns locally

Your Chromeyour real browser and logins

Pages, sessions, passwordsread and acted on locally

Up to 2.2x

faster task completion vs Playwright MCP. July 2026 checkout: 62.7s to 28.1s.

Up to 86%

fewer estimated tool-reply tokens vs Playwright MCP. July 2026 checkout: about 4,586 to 650. Not total model usage.

Up to 75%

fewer MCP requests vs Playwright MCP. October 2026 profile: 4 to 1, using the unreleased Reflex build.

Selected results from separate benchmarks. See all results

Pay for what you use. Paid credits never expire.

Full pricing details →

Free

$0

Kick the tires, no card.

• 25 calls with no account at all
• 30 more credits when you sign up
• ~10-15 tasks · free credits expire in 14 days

Starter

$9one-time

For occasional flows.

• 150 credits
• ~50-75 tasks
• $0.12-0.18 per task

Most popular

Pro

$19one-time

Best value for steady use.

• 500 credits
• ~165-250 tasks
• $0.08-0.11 per task

Power

$49one-time

For heavy, daily automation.

• 1,800 credits
• ~600-900 tasks
• $0.05-0.08 per task

Questions, answered straight.

Everything runs locally: the MCP server, your Chrome, your logins, the pages. The only data that reaches our servers is your email (for your account), your API key, and a counter of tool calls for credit metering. Page content, URLs you visit, credentials, and session cookies never leave your machine; there is no code path that could send them. Payments are handled by Paddle, our merchant of record; we never see card numbers. Our privacy policy is short because there is almost nothing to disclose.

Up to 2.2x faster. Up to 86% fewer tool-reply tokens. Up to 75% fewer MCP requests.

Selected results from separate benchmarks versus Playwright MCP. Speed and estimated tool-reply tokens: July 2026 checkout. MCP requests: October 2026 profile task with an unreleased Reflex build. Results vary by workload. See the measurements.

Installed in 2 minutes. Your pages stay yours. Or install first and skip the account.