Reflex MCP Server
A faster, parallel browser for AI agents: it drives your own Chrome from Claude Desktop or any MCP client, on fewer round trips and tokens than Playwright MCP.
Documentation
For Claude Desktop, Cursor, and any MCP client
A faster browser for your AI agent
Reflex drives your real Chrome for Claude, Cursor, or any MCP client. Tasks finish about 3.5× faster than Playwright MCP, you can run many browsers at once, and each task costs a fraction of the tokens. Every page stays on your machine.
Research products, fill forms, compare prices, scrape tables, all in plain English.
- ~3.5× faster, end to end
- Run browsers in parallel
- ~4× fewer tokens
Add Reflex to your client in one click.
Add to Cursor Add to VS Code Claude Code Claude Desktop
One click in your client, then reflex_auth to sign in.
Free to start: 30 credits (~10-15 tasks), no card. Your agent signs you in on the first run, or grab a key first. Read the benchmark →
0:00 / 0:001×
Same task, side by side: Reflex vs Playwright MCP. Finishes ~3.5x faster, on a fraction of the tokens.
Head-to-head
Watch the token race.
Wikipedia: search an article, open its revision history
run it again
Playwright MCP5/5 calls
tokens into context~30K
Reflex2/2 calls
tokens into context~8K
One real flow above, measured 2026-06-12. Across all three verified flows: 6 calls / ~13K tokens vs 14 calls / ~56K tokens (~2 calls per flow with Reflex).
Getting started
Two minutes to your first task.
your MCP client
# 1: install Reflex
one click into Cursor or VS Code, or npx -y reflex-browser mcp in your MCP config
# 2: sign in once
ask your agent to sign in. It opens your browser once and saves a key locally. 30 free credits, no card
# 3: ask your agent, in plain English
> Compare the prices of these three products and tell me which has free shipping.
Reflex batches the whole flow into one call and reports back what changed, not the whole page.
Benchmarks
Measured, not promised.
From our published head-to-head against Playwright MCP, run on live sites with no AI on either side. Every number, and how to reproduce it, is on the benchmarks page.
| Playwright MCP | Reflex | |
|---|---|---|
| Tool calls, 3 measured flows | 14 | 6 |
| Tokens into context, same flows | ~56K | ~13K |
| Flows completed, of 6 attempted | 3 | 5 |
| One look at a Wikipedia article | ~31K tokens | ~4K tokens |
| One look at the worst page tested (W3C CSS spec) | ~169K tokens | ~7K tokens |
| Re-reading an unchanged page | ~16K tokens | 91 characters: "(page unchanged)" |
Measured 2026-06-12. See every number and how to reproduce it.
Clients like Claude Desktop pay that snapshot cost on every look. Reflex compresses the page instead, so your agent keeps its context for the real work. Playwright MCP is free and better for iframes and other browsers; Reflex wins when every look costs you context. Full methodology and the reproduce command are on the benchmarks page.
Parallel sessions
Run as many browsers as you want, at once.
Give any call a session name and Reflex spins up a separate, isolated browser for it, on demand and free. One agent can research ten sites at the same time; a swarm of subagents can each drive their own.
Playwright MCP shares a single browser, so parallel agents fight over the same tab. With Reflex you never have to choose between speed and isolation.
three browsers, one connection
reflex_open(url, session: "flights")
reflex_open(url, session: "hotels")
reflex_open(url, session: "cars")
# three isolated browsers, running side by side
Agent-native
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.
Privacy
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.
Your machine stays here
Claude Desktop
or Cursor, Claude Code, any MCP client
Reflex MCP server
runs locally
Your Chrome
your real browser and logins
Pages, sessions, passwords
read and acted on locally
API key + call count
pages never cross
Reflex servers
- Is this key valid?
- Credit balance
- Usage counts
- Paddle payments
No path exists for your pages, logins, or sessions to reach us.
~3.5x faster
end to end on 5 live-site tasks, with a real agent driving (vs Playwright MCP)
7.9x fewer tokens
per page look vs Playwright MCP, averaged across 12 live sites
0 tokens
to re-run a saved flow (deterministic replay, no model in the loop)
See every measured number and how to reproduce it
Pricing
Pay for what you use. Paid credits never expire.
Full pricing details →
Free
$0
Kick the tires, no card.
- 30 credits · expires in 14 days
- ~10-15 tasks
Get your key
Starter
$9one-time
For occasional flows.
- 150 credits
- ~50-75 tasks
- $0.12-0.18 per task
Buy Starter
Most popular
Pro
$19one-time
Best value for steady use.
- 500 credits
- ~165-250 tasks
- $0.08-0.11 per task
Buy Pro
Power
$49one-time
For heavy, daily automation.
- 1,800 credits
- ~600-900 tasks
- $0.05-0.08 per task
Buy Power
FAQ
Questions, answered straight.
Is my data safe? What do you see?
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.
Why credits instead of a subscription?
What happens when I run out of credits?
Does it work with ChatGPT?
Why not just use Playwright MCP? It's free.
Can I use my existing Chrome logins?
How many credits does a task cost?
Does Reflex need an internet connection?
Do credits expire?
What's your refund policy?
Ready when you are
Same browser tasks. ~13K tokens, not ~56K.
Get 30 free credits
Installed in 2 minutes. Your pages stay yours.