Agent Browser MCP Server

by scriptmasterlabs Your server? Claim it

answering

Agent Browser is answering right now. Last checked 12 min ago. It exposes 6 tools.

A real Chromium browser agents pay for per action in USDC via x402 — hosted MCP, free local stdio.

Uptime history 6 days of history · worst day 99%

6 days agonow

100.0%

Uptime 24h

91 of 91 checks

Tools

read from the server

279 ms

Response time

average over 24h

open, no key

Access

streamable-http

What changed 6

Every tool that appeared, vanished or quietly changed what it asks for. Recorded since 1 November 2026. No other catalogue keeps this.

1 Nov 6 tool descriptions were rewritten browser_act, browser_close, browser_extract and 3 more

Agent Browser missed one check this week

Everything else answered, so this is steady rather than shaky. We check every 15 minutes, which is how a one-off gets told apart from the start of a pattern, and how you hear about the next one within the hour instead of from your users.

Connect this server

Endpoint below is the one we actually reach during checks — not the one copied from a README. Last verified 12 min ago.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add agent-browser --transport http https://agent-browser-r7d2.onrender.com/mcp

Settings → Connectors → Add custom connector, then paste this address

https://agent-browser-r7d2.onrender.com/mcp

~/.codex/config.toml

[mcp_servers.agent-browser]
url = "https://agent-browser-r7d2.onrender.com/mcp"

.cursor/mcp.json

{
  "mcpServers": {
    "agent-browser": {
      "url": "https://agent-browser-r7d2.onrender.com/mcp"
    }
  }
}

.vscode/mcp.json

{
  "servers": {
    "agent-browser": {
      "type": "http",
      "url": "https://agent-browser-r7d2.onrender.com/mcp"
    }
  }
}

Available tools 6

Read directly from the server with tools/list, grouped by what they act on. If a tool disappears, we record the date.

browser

browser_act

Use for: interacting with the page — click, fill, type, select, submit, press. Returns the resulting page title, URL and text so you can verify the action landed. Don't use when: the target element is not on the current page — navigate or snapshot first. This tool can change remote state (it can submit forms). Paid: $0.01 USDC per call via x402 on Base.

browser_close

Use for: ending a session and freeing its browser. Sessions also expire automatically after 10 idle minutes. Free on every door — closing is never charged. Free.

browser_extract

Use for: pulling repeated elements (prices, titles, links) from the page a session is on, via a CSS selector, or the full page text when no selector is given. Returns one string per matched element. Don't use when: the page has not been loaded yet — call browser_navigate first. Paid: $0.005 USDC per call via x402 on Base.

browser_navigate

Use for: loading a web page in a real Chromium browser and reading it. Returns the page title, final URL and a clean text extract (up to 8000 chars). Don't use when: you only need raw HTML or an API response — a plain HTTP fetch is cheaper. Errors are structured: NAV_TIMEOUT, NAV_FAILED, INVALID_URL. Paid: $0.005 USDC per call via x402 on Base.

browser_screenshot

Use for: visual verification — layout, images, charts, CAPTCHA presence, or evidence of page state. Returns a PNG image (JPEG if the PNG exceeds 2.5MB). Don't use when: you only need the page's content or structure — browser_extract and browser_snapshot are far cheaper in tokens. Paid: $0.02 USDC per call via x402 on Base.

browser_snapshot

Use for: understanding page structure cheaply and deterministically — returns the accessibility tree (roles, names, states) as compact YAML instead of pixels or raw HTML. This is the lowest-token way to decide what to click or fill next. Don't use when: you need visual layout or images — use browser_screenshot. Paid: $0.005 USDC per call via x402 on Base.

Endpoints

URL	Transport	State	Latency	Checked
https://agent-browser-r7d2.onrender.com/mcp	streamable-http	answering	230 ms	12 min ago

Alternatives to Agent Browser

same job, measured the same way

Uindow

by uindow

Real signed-browser automation for AI agents, over a local stdio MCP server.

130 installs/wk local only

vibatchium

by trueoriginlabs

Stealth browser automation for AI agents — real Chrome, N parallel persistent logged-in sessions.

179 installs/wk local only

x402-snap

by zadengg

Pay-per-call browser rendering and x402 marketplace ranking for AI agents, billed via USDC.

3 tools answering

SnapRender

by user0856

Local stdio MCP server for SnapRender screenshots. Hosted version: com.snap-render.app/snap-render

84 installs/wk local only

BrowserMesh

by scrolldynasty

Isolated multi-session Chromium runtime for external MCP clients over stdio.

49 installs/wk local only

unbrowser by Unchained

by protostatis

Chrome-free MCP web access for agents with low-token page maps and browser escalation hints.

137 installs/wk local only

Yad Agent MCP

by holistis

MCP wrapper for Yad, a local browser-automation companion, for coding agents.

45 installs/wk local only

Stealth Agent Browser

by ykshah1309

Stealth Chromium MCP server with hybrid AOM + Set-of-Mark vision and Readability extraction.

64 installs/wk local only

Agent Browser — questions

Answers built from our own checks of this server.

What can Agent Browser do?

It exposes 6 tools, read directly from the server on our last check. Among them: browser_act, browser_close, browser_extract, browser_navigate, browser_screenshot, browser_snapshot. The full list with descriptions is on this page — we take it from the server itself via tools/list, not from a README. How MCP servers expose tools in the first place →

Is Agent Browser working right now?

We send a real MCP handshake every 15 minutes. Over the last 24 hours 91 of 91 checks got a reply (100.0%), average response time 279 ms. The bar chart above shows every period we have measured.

How do I connect Agent Browser?

Copy the ready config from this page. We generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each in the form that client actually reads. It is a remote server, so there is nothing to install — the client connects to the address.

Does Agent Browser need an API key?

No. Agent Browser completed a full MCP handshake with us as an anonymous client and listed its tools without asking for anything. All 6 of them are readable on this page. This is what we observed, not what the docs claim.

How fast is Agent Browser?

It answers our handshake in 279 ms on average, which is faster than 50% of all working MCP servers we measure. The comparison comes from our own checks across the whole registry, every 15 minutes.