Browser Use
by browser-use
Lets AI do web tasks for you, such as filling forms, searching and extracting data, in the maker’s cloud browsers or on your computer.
Computer or cloud★ 120,087MITUpdated 17 days ago
Install
Render MCP
Overview
Description from the maker (original English)
Hosted browser for AI agents: screenshots, post-JS DOM, console, WCAG. No install, no API key.
PopNx MCP’s three pillars
These three are never merged into one score: opinions, measurements and popularity are different things.
- User voiceiNo reviews yetReviews open together with accounts in a later step
- Our basic checksi1 of 1 passedChecked from public information; code not scanned yet
- UsageiNot measured yet★ –
What you can do with it
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
- Connection: Runs in the cloud
- Transport: Streamable HTTP
- Category: Web & browsers
Install
Pick the AI app you use, then copy the settings.
Before you install
- Basic checks: 1 of 1 passed
- Runs on the maker’s server: what you ask it goes through their server.
- The registry lists no key to fill in.
You need
- Runs in the cloudNothing to install; it connects over the internet
Which app do you use?
Pick your app above. We remember it, so next time the button says “Install in …”.
Works in Claude on the web, desktop and mobile:
- Open Settings → Connectors
- Press Add custom connector
- Paste the address below and press Add
- If it asks you to sign in, sign in with the maker
https://render.makermargins.com/mcpRun this in your terminal
claude mcp add --transport http render https://render.makermargins.com/mcpOr copy the settings yourself
Paste into .cursor/mcp.json in your project, or ~/.cursor/mcp.json
{
"mcpServers": {
"render": {
"url": "https://render.makermargins.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
Or copy the settings yourself
Paste into .vscode/mcp.json in your project
{
"servers": {
"render": {
"type": "http",
"url": "https://render.makermargins.com/mcp"
}
}
}Your browser asks to open the app, then the app shows the settings and asks you to confirm. Key values are left empty for you to fill in.
ChatGPT connects only to servers on the internet:
- Open ChatGPT on the web → Settings → Connectors (Apps)
- Press Create or Add (some plans need Developer mode under Advanced first)
- Paste the address below, give it a name and save
- If it asks you to sign in, sign in with the maker
https://render.makermargins.com/mcpMenu names can differ slightly by plan and over time.
Your choice stays on this device in a cookie; no account needed.
These settings are generated from the maker’s registry entry. If the README says otherwise, follow the README.
What it can do
We have not read this server’s tool list yet; we check endpoints in rotation.
Basic checksi
We check information anyone can see; we have not read the code. Checks that do not apply are left out of the count. · Checked Nov 6, 2026
- ✓ Pass
Maker matches the repo
The registry name was verified with the GitHub account RodRomer, which owns the repo
- … Not checked yet
Still maintained
We have not read this repo from GitHub yet
- … Not checked yet
Has a licence
We have not read this repo from GitHub yet
- … Not checked yet
Endpoint responds
Not checked yet; we check endpoints in rotation
- … Not checked yet
Sign-in with OAuth
Not checked yet; we check endpoints in rotation
- … Not checked yet
No hidden instructions in tool descriptions
Not checked yet; we read the tool list when we check the endpoint
Compared with others in Web & browsersi
- More stars than 0% of the other 878 servers in this category
- Published to the registry more recently than 35% of the other 878 servers in this category
- Basic checks equal to or better than 100% of the other 878 servers in this category
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
Common questions
Is Render MCP safe?
It passed 1 of 1 applicable basic checks. We have not read the code. Before adding a key or token, see what access the server asks for and use a key with only the permissions you need.
What keys or codes does it need?
The registry does not list a required key, though some servers ask you to sign in on first use.
Does it run on my computer or in the cloud?
It runs in the maker’s cloud. Connect over the internet with nothing to install, but what you send passes through the maker’s servers.
Is it still maintained?
The GitHub repo last changed –, and the latest version (0.7.4) reached the registry 2 months ago.
Which apps can use it?
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code. It connects by URL, so apps that accept remote MCP servers work too, such as ChatGPT in developer mode.
What can I use instead?
In the same category: Browser Use, Chrome DevTools MCP, MCP Server Browser
Alternatives
Servers in the same category from other makers, sorted by stars.
Reading a card:★ GitHub starsiThree pillars: reviews · checks · usageiUpdated = latest version published to the registryi
Chrome DevTools MCP
by ChromeDevTools
Lets AI use Chrome’s developer tools to inspect pages, find what makes them slow and spot errors. Made by the Chrome DevTools team.
Runs on your computer★ 54,821Apache-2.0Updated 15 days ago
Install
MCP Server Browser
by bytedance
MCP server for browser use access
Runs on your computer★ 39,550Apache-2.0Updated 14 months ago
Install
README from the maker
Open the README
Copied from the maker’s repo as written. PopNx MCP has not reviewed or endorsed it. HTML, images and scripts are removed. Links lead off this site.
render-mcp
Gives an AI agent a real browser. Screenshots, PDFs, and the HTML a page produces *after* JavaScript has run.
No API key. No signup. No account. Point your client at a URL and it works.
https://render.makermargins.com/mcpWhy this exists
An agent can fetch a URL. It cannot *see* one.
Ask an assistant to check whether a page looks right, or to read a site built with React, and it hits a wall: a plain HTTP fetch returns an empty shell and a loading spinner. The content is built by JavaScript that never runs.
The usual answer is a rendering API — but every one of them requires you to sign up, verify an email, and paste an API key. An agent working on its own can't do any of that. It has no inbox and no card. A free tier it cannot register for is worth nothing to it.
This server needs none of it. It runs on Cloudflare's network, launches a real headless browser, and hands back what the page actually looks like.
Install
Claude Code — as a plugin (one command, and updates arrive automatically)
/plugin marketplace add RodRomer/render-mcp/plugin install render@render-mcp
Claude Code — directly
claude mcp add --transport http render https://render.makermargins.com/mcpClaude Desktop, Cursor, and other clients — add to your MCP config:
{"mcpServers": { "render": { "type": "http", "url": "https://render.makermargins.com/mcp" } } }
That's the whole setup. Nothing to install, nothing to configure, no credentials.
Tools
screenshot_url
See a page as a person would. Returns a PNG.
| Argument | Type | Notes |
|---|---|---|
url | string | Required. Absolute, including https:// |
full_page | boolean | Capture the whole scrollable page. Default false |
width | number | Viewport width, 320–2560. Default 1280 |
height | number | Viewport height, 240–2000. Default 800 |
Good for: confirming a deployment looks right, checking a layout, seeing what a user sees.
rendered_html
The DOM *after* JavaScript has executed. Returns HTML text.
| Argument | Type | Notes |
|---|---|---|
url | string | Required. Absolute, including https:// |
wait_for | string | CSS selector to wait for, if content loads late |
max_chars | number | Truncation limit, 1,000–500,000. Default 100000 |
Good for: single-page apps, anything where a plain fetch returns a shell.
page_diagnostics
Load a page and report what went wrong: JavaScript console errors, failed network requests, and any 4xx/5xx responses. Returns a readable summary.
| Argument | Type | Notes |
|---|---|---|
url | string | Required. Absolute, including https:// |
include_warnings | boolean | Include warnings and info, not just errors. Default false |
width | number | Viewport width, 320–2560. Default 1280 |
height | number | Viewport height, 240–2000. Default 800 |
Good for: a deployment that might have shipped a bug, a page that loads blank, a site that "looks broken" and you need to know why.
Stated honestly: this is not a rare capability. Microsoft's @playwright/mcp returns console messages, and Google's chrome-devtools-mcp returns them with source-mapped stack traces across 29 tools. Both are excellent, both are better resourced than this, and between them they are downloaded around 34 million times a month. If you can run a local process, use one of them.
The one thing neither can do is run where nothing can be installed. They need npx, Node, and browser binaries, or a local Chrome. This needs a URL. That is the whole of the difference, and it only matters if you are in that situation.
inspect_element
Answers *"why isn't this element showing where I expect?"* for a CSS selector.
| Argument | Type | Notes |
|---|---|---|
url | string | Required. Absolute, including https:// |
selector | string | Required. CSS selector, e.g. .buy-button |
max_matches | number | How many matches to report, 1–10. Default 3 |
width | number | Viewport width, 320–2560. Default 1280 |
height | number | Viewport height, 240–2000. Default 800 |
Leads with a diagnosis, then the numbers: resolved box model, computed display / visibility / opacity / position / z-index, colours, whether it's inside the viewport, and whether another element is covering it.
The useful part is that it walks *up* the tree. The usual reason an element is missing is not the element — it's an ancestor, and the answer you want is *which* one:
--- match 1: button#buyHIDDEN BY AN ANCESTOR — div.modal.panel has display:none. The element itself is fine.
It also catches the case no single property reveals. Content inside a closed keeps a normal box and reports display:block, visibility:visible, opacity:1 — everything looks fine, and it still doesn't paint:
NOT RENDERED — it sits inside details.fees, which is not displaying itscontents because of a closed . Box: 70x27 ... display:block visibility:visible opacity:1
Good for: an element that "should be there", a click landing on the wrong thing, verifying a CSS change actually applied. Cascade resolution and layout cannot be derived from reading HTML and CSS — this is the one thing a browser is strictly required for.
url_to_pdf
Render a page to PDF as a browser would print it.
| Argument | Type | Notes |
|---|---|---|
url | string | Required. Absolute, including https:// |
landscape | boolean | Default false |
Good for: archiving a page, turning a rendered report into a document.
What it won't do
Stated plainly, so an agent doesn't waste calls discovering them:
- No private networks. Loopback, RFC1918 ranges,
169.254.x.x,.internaland.localhostnames are refused. This server runs inside Cloudflare's network and an unvalidated URL would be a server-side request forgery. - No logins. There's no session, so anything behind authentication renders as its login page.
- 20 second navigation limit. Very slow pages will time out.
- No JavaScript injection. It renders pages; it doesn't run your code on them.
Failures come back as readable text explaining what went wrong, not as protocol errors — so an agent can route around them rather than crashing.
Privacy
URLs and page content are never stored or logged. Each call launches a browser, does the work, hands back the result, and closes it. Nothing about *what* you asked for is retained.
One thing is counted, and it's worth stating precisely rather than hiding behind "anonymised":
| Recorded | Not recorded |
|---|---|
Which tool ran (screenshot_url, …) | The URL, or any part of it |
How it ended (ok, timeout, capacity, …) | Your IP address |
| How long it took, in milliseconds | Any header, cookie or credential |
| Any page content, image or PDF |
That's three fields with no way to tie them to a request, a person or a site. The function that writes them is never handed the URL in the first place, so it cannot record one by accident — see count() in src/index.js.
It exists for one reason: this server is free, and the only way to decide whether it's worth keeping alive is knowing whether anything calls it.
The counts are public — no login, no dashboard:
https://render.makermargins.com/statsDevelopment
npm installnpm test # 279 tests, no network or browser needed npm run test:dom # 39 DOM tests, headless Edge/Chrome, no network npm run dev # local worker npm run deploy # to Cloudflare
Two layers, both tested outside their host:
- `src/protocol.js` — the MCP request/response surface as pure functions, with no Cloudflare or browser dependency. Every URL validation and SSRF rule is proven under plain Node before anything deploys.
- `src/inspect-page.js` — the half of
inspect_elementthat runs *inside* the page. It closes over nothing, so any real DOM can execute it. Its tests build fixture pages in headless Edge and assert on real computed styles and real geometry. A mocked DOM would prove nothing here: the entire premise of the tool is that these values only exist once a browser has resolved the cascade and run layout.
src/index.js is a thin shell — transport in, browser work out, prose formatting on the way back.
If Node isn't installed, npm run test:nonode runs the protocol suite in headless Edge instead. It strips only the export/import keywords and executes the same source.
When testing against a live page, use a neutral URL
Use https://example.com — it is reserved by IANA for exactly this — or httpstat.us for error paths. Do not point live tests at `makermargins.com`.
The reason is not politeness. That site has Cloudflare Web Analytics, whose beacon is injected into HTML responses for browser-like requests. This server drives a real headless browser, so every screenshot or audit of that site executes the beacon and registers as a visitor — inflating the traffic figures of the very asset the numbers are meant to measure. An instrument that counts its own operator measures nothing.
Status
Early and free. Built to find out whether MCP registry discovery actually works. If it gets used, it'll be maintained; if it doesn't, that's a useful answer too.
Issues and pull requests welcome.
How this was built
Written by Claude, directed by a human, and stated here rather than left to be inferred.
That is worth knowing when judging it, so the relevant facts are these: 318 tests cover the protocol surface, the routing table, the usage counter, the landing page and the plugin manifests, and the parts that need a real browser are tested against real fixture pages rather than a mock DOM. Every platform claim in this README was checked against a primary source, and several widely-repeated ones turned out to be wrong.
None of that makes it good on its own — but it is checkable, which is more useful than a promise.
Licence
MIT