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.
Description from the maker (original English)
Drive Argus anti-detect browser profiles: isolated identities with their own fingerprint and proxy.
These three are never merged into one score: opinions, measurements and popularity are different things.
We have not written a plain-language summary for this one yet. Below are the facts we read from the registry.
Pick the AI app you use, then copy the settings.
The maker has not listed install details in the registry. See the maker’s README below.
Runs on your computer; the tool list appears in your AI app after you install it.
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 7, 2026
The registry name was verified with the GitHub account pochtmanr, which owns the repo
We have not read this repo from GitHub yet
We have not read this repo from GitHub yet
This one runs on your computer; there is no internet endpoint
Runs on your computer and uses local settings instead
Runs on your computer; we can only read tool lists from internet endpoints
Compared with every active server in this category in the registry. Stars count only when the publisher owns the repo.
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.
The registry does not list a required key, though some servers ask you to sign in on first use.
It runs on your computer. Your AI app starts it when needed, and data does not pass through the maker’s servers (unless it calls an online service itself).
The GitHub repo last changed –, and the latest version (1.0.72) reached the registry 3 months ago.
Apps that support MCP, such as Claude Desktop, Claude Code, Cursor and VS Code.
In the same category: Browser Use, Chrome DevTools MCP, MCP Server Browser
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
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.
Lets AI use Chrome’s developer tools to inspect pages, find what makes them slow and spot errors. Made by the Chrome DevTools team.
MCP server for browser use access
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.
Documentation, the assistant skill briefs, and the MCP registry manifest for Argus, an anti-detect browser for managing hundreds of isolated browser profiles — each with its own fingerprint, proxy and cookie jar.
Which Argus this is. Argus is published by Simnetiq Ltd (UK company
number 16861177) at www.browserargus.com.
Other companies and software products share the name Argus and are unrelated
to this one.
This is a local API. It listens on loopback on the machine running Argus, and nothing off that machine can reach it. There is no hosted web API.
The Argus MCP server ships inside the launcher's own application bundle and is started through it with ELECTRON_RUN_AS_NODE. There is no npm package, no npx command and nothing new listening: it speaks JSON-RPC over stdin and stdout to the client that launched it, and reaches the local API on your behalf.
For most clients the launcher writes the config file for you and shows you the path first. Two of them have no file it can write, and hand you a snippet instead. See Integrations and MCP setup.
This repository is the documentation for that server, not the server.
| Path | What it is |
|---|---|
docs/api-reference.md | All 130 endpoints and 143 tools — paths, fields, curl examples, status codes. |
docs/openapi.json | The same table as an OpenAPI 3.1 spec, for generating a client. |
docs/mcp-tools.md | The tool list an MCP client receives, and which endpoint each one fronts. |
skills/ | The briefs the in-app assistant runs on, as readable JSON. |
agents/ | Drop-in rules for your own CLAUDE.md, AGENTS.md or .cursorrules. |
server.json | The MCP registry manifest. |
ARGYS_API_TOKEN — that is the name the launcher tells you to use and the one the MCP server reads from the environment.curl -s "http://127.0.0.1:39219/v1/profiles" \
-H "Authorization: Bearer $ARGYS_API_TOKEN"
The first call from a new client raises an approve-or-deny card in the launcher and blocks until you answer it.
To drive it from a coding agent instead, connect an MCP client — Claude Code, Codex, Cursor, Gemini CLI, Windsurf, VS Code, Zed, OpenClaw, Hive and others are supported — and the 143 tools appear on their own.
skills/An Argus *skill* is the working brief the in-app assistant loads for one job: instructions, worked examples, a reference shelf, and the pack of tools it may reach.
Every brief in skills/ already ships inside Argus. They are published here to be read and to be adapted — not installed, because you already have them. Each file is in the shape POST /v1/skills/save accepts, so editing one and posting it creates *your own* custom skill:
curl -X POST "http://127.0.0.1:39219/v1/skills/save" \
-H "Authorization: Bearer $ARGYS_API_TOKEN" \ -H "Content-Type: application/json" \ -d @skills/proxies.json
skills/README.md is the roster: every brief, what it is for, and which pack of tools each one carries.
Note what the files deliberately omit:
toolPack, so posting one as-is gives a skill with documentation and navigation tools only. The brief is still the useful part. skills/README.md marks which is which, brief by brief.MIT — see LICENSE. The grant covers the contents of this repository: the generated documentation, the agent rules and the skill briefs. Argus itself — the launcher, the hardened browser and the MCP server — is proprietary and is not part of this repository.