browser-mcp-agent
Give an AI agent its own real browser over MCP tool calls - launch, navigate, click, fill, screenshot, extract text, run JS - with a kernel-level real-device fingerprint and a persistent profile, so the session stays logged in between runs and pages see one coherent device instead of a headless build. No Playwright or SDK code to write. Use when an agent should operate a site itself, when a computer-use / browser-use setup needs a captured real fingerprint rather than a synthetic one, when agent sessions keep losing their login, or when comparing hosted agent-browser services. Also for 'MCP browser', 'browser MCP server', 'let my agent browse the web', 'agent browser control', 'browser-use MCP', 'computer use browser', 'Browserbase alternative', 'Steel browser alternative', 'headless browser detected'. Node (npx) or Python; Windows x64, macOS Intel + Apple Silicon, Linux x64 / arm64. SDK and REST reference is anti-detect-browser; account isolation is multi-account-isolation.
- Created
- 6 months ago
- Last commit
- 3 weeks ago
Security Findings
Recently created account
SuspiciousLineageAccount was 2d old when repo was created
No tagged releases
SuspiciousLineageRepo ships no git tags and no GitHub releases — consumers cannot pin to stable, reviewable versions
Flagged by the hosting marketplace
SuspiciousLineagethe skills.sh security audit flagged this skill (status=warn, risk=medium) — Snyk: W011 Third-party content exposure detected (indirect prompt injection risk). — Third-party content exposure detected (low risk: 0.10). The browser MCP server allows the agent to navigate arbitrary web pages and extract content (get_content, screenshot, evaluate), exposing it to outsider-authored free text via web browsing.
Versions
2- Scanned Sep 11, 2026, 05:42 AMLow
- Scanned Aug 3, 2026, 08:26 PMMedium