What is mcp-browser-use AGENTS.md?

A set of development instructions for an MCP server that lets AI agents automate web browsers through browser-use. MCP is a protocol for connecting agents to external tools, and this server uses HTTP transport.

Use it when developing the browser server, its CLI, configuration, research workflows, provider integrations, or browser-automation skills.

It defines the required workflow and project structure so browser automation changes are formatted, checked, typed, and tested consistently.

How Saik0s/mcp-browser-use configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Saik0s/mcp-browser-use. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Saik0s/mcp-browser-use/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Saik0s/mcp-browser-use

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/saik0s/mcp-browser-use/agents-md/github.svg)](https://agentmods.dev/instructions/saik0s/mcp-browser-use/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/saik0s/mcp-browser-use/agents-md"><img src="https://agentmods.dev/badge/instructions/saik0s/mcp-browser-use/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/saik0s/mcp-browser-use/agents-md"><img src="https://agentmods.dev/badge/instructions/saik0s/mcp-browser-use/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,631 This file is loaded in full into every session.

When invoked 1,631 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01631	$0.01631
Opus 5.5	$0.00652	$0.00652
Sonnet 5.5	$0.00326	$0.00326
Haiku 4.5	$0.00163	$0.00163

Measured 2mo ago against content hash e4d385f220c8, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

mcp-browser-use AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 233 lines

How it starts

The opening of the file, as written. The whole thing — 233 lines — stays where its author put it; the contents beside it link to each section on GitHub.

MCP Browser Use Development Guidelines

Audience: LLM-driven engineering agents and human developers

MCP server that wraps browser-use for AI-driven browser automation. HTTP-only transport (stdio deprecated due to timeout issues with long-running browser tasks).

Required Development Workflow

CRITICAL: Always run these commands before committing:

uv sync                    # Install dependencies
uv run ruff format .       # Format code
uv run ruff check .        # Lint check
uv run pyright             # Type checking
uv run pytest              # Run tests

All checks must pass - this is enforced by pre-commit hooks. Alternative: just check

Repository Structure

Path	Purpose
`src/mcp_server_browser_use/`	Library source code
`├─ server.py`	FastMCP server + MCP tools
`├─ cli.py`	Typer CLI for daemon management
`├─ config.py`	Pydantic settings
`├─ providers.py`	LLM factory (12 providers)
`├─ observability/`	Task tracking (SQLite persistence)
`├─ research/`	Deep research workflow
`└─ skills/`	Machine-learned browser skills
`tests/`	Pytest test suite
`docs/`	Design documents
`examples/`	Example usage

Core MCP Tools

Tool	Purpose	Duration
`run_browser_agent`	Execute browser automation	60-120s
`run_deep_research`	Multi-search research	2-5 min
`skill_list/get/delete`	Skill management	<1s
`health_check`	Server status	<1s
`task_list/get/cancel`	Task management	<1s

Writing Code

Style Guidelines

Python 3.11+ with full type annotations
Line length: 150 characters
Use async/await for I/O operations
Follow existing patterns - check similar code first
Prioritize clarity over cleverness

Code Standards

Type hints required for all functions
Docstrings for public APIs
No any types - use specific types
Async testing with anyio/pytest-asyncio

Read the full file on GitHub · 233 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 233 lines · 1,631 tokens per session scan A e4d385f220c8

Subscribe to this mod's changes

mcp-browser-use AGENTS.md is an instructions file published in the GitHub repository Saik0s/mcp-browser-use (972 stars, last pushed 8mo ago), licensed MIT. It adds 1,631 tokens to every session, about $0.0065 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-30.

mcp-browser-use AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
mcp-browser-use AGENTS.mdSaik0s/mcp-browser-use	Instructions file	972	8mo ago	MIT	A	1,631	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

mcp-browser-use: Instructions file for Codex