Browser Tools
This skill allows you to interact with web pages directly – navigate, extract data, and more – boosting automation and scraping capabilities.
Install on your platform
We auto-selected Claude Code based on this skill’s supported platforms.
Run in terminal (recommended)
claude mcp add browser-tools npx -- -y @trustedskills/browser-tools
Or manually add to ~/.claude/settings.json
{
"mcpServers": {
"browser-tools": {
"command": "npx",
"args": [
"-y",
"@trustedskills/browser-tools"
]
}
}
}Requires Claude Code (claude CLI). Run claude --version to verify your install.
About This Skill
What it does
This skill provides a security wrapper around the agent-browser tool, enhancing its functionality for interacting with web pages. It enables AI agents to navigate websites, extract data, and perform actions within browser environments. The primary purpose is to add safety guardrails while leveraging the full capabilities of the underlying agent-browser tool.
When to use it
- When needing to interact with Single Page Applications (SPAs) or interactive web pages that require a browser environment.
- When login authentication and state management are required for accessing web content.
- When dynamic web content needs to be handled, utilizing wait commands based on element presence or text content.
- For tasks involving data extraction from websites where
WebFetchorTavilyare insufficient. - To discover and install capability packs directly within the agent environment.
Key capabilities
- Navigation & Interaction: Full command set for web page interaction (refer to upstream
agent-browserdocumentation). - Data Extraction: Ability to extract data from web pages.
- Semantic Locators: Uses accessibility trees (
findByRole) for more robust element identification, less reliant on CSS selectors. - Debugging Tools: Screenshot annotation with ref IDs and role labels.
- Skill Discovery & Chat:
agent-browser skills list/getto discover and install capability packs; natural language interaction viaagent-browser chat. - Cloud Provider Integration: Supports AWS Bedrock AgentCore cloud browser (
--provider agentcore). - Dashboard Access: Embedded dashboard for inspection (accessible via
agent-browser dashboard).
Example prompts
agent-browser open "http://myapp.localhost:1355"- Opens a specific URL in the browser.agent-browser find button[role="button"]- Locates a button element using semantic role.agent-browser chat "Click the submit button"- Uses natural language to drive actions within the browser.
Tips & gotchas
- Upstream Documentation: Refer to the
agent-browserdocumentation for the complete command reference and detailed usage patterns. This skill primarily adds security features. - Stable URLs: Use Portless (
npm i -g portless) for stable local development URLs instead of relying on potentially changing ports. - Security Focus: This skill prioritizes safety guardrails; remote providers are treated as egress surfaces with restricted network routing.
Tags
TrustedSkills Verification
Unlike other registries that point to live repositories, TrustedSkills pins every skill to a verified commit hash. This protects you from malicious updates — what you install today is exactly what was reviewed and verified.
Security Audits
| Gen Agent Trust Hub | Pass |
| Socket | Pass |
| Snyk | Pass |
🌐 Community
Passed automated security scans.