mcp · handle mcp_server_browserbase
browser_agent_py · job 77%unbrowser by Unchained · job 78%AgentSmith · job 74%asteroid · job 74%humanbrowser · job 82%oculo · job 79%Cognitive Browser · job 71%BrowserCat Remote Browser Automation · job 83%Kernel · job 71%skyvern_ai · job 70%browseros · job 73%Browser Infrastructure for AI Agents · job 74%playwright_mcp · job 81%chrome_playwright_mcp · job 70%AgentLock Browser · job 72%webfetch_mcp · job 74%open_computer_use_2 · job 74%zen_mcp · job 71%ai_browser_mcp · job 76%drissionpage_mcp_server · job 73%glance · job 75%screenpilot · job 74%drissionpage_mcp · job 72%camofox_mcp · job 76%chromedp_mcp · job 70%playwright_browser · job 76%webhosting_mcp · job 75%hunch · job 73%pilotbrowsemcp · job 70%ruyi_mcp · job 72%multi_browser_mcp · job 79%Nexus Browser MCP · job 84%Aether Browser MCP · job 78%stealth_browser_mcp · job 73%Percentages are graph-similarity metadata, not suitability scores. A graph edge answers “is it connected” — plan fit and comparable cost are checked below.
Pick the exact reference and alternative series. Each history is separate; gaps stay gaps.
This view calls the same get_evidence tool your agent would — chart, table and MCP response describe the same records. Watch the reference series