ScrAPI MCP · job 73%Kernel · job 72%browser_agent_py · job 71%browseros · job 75%AgentSmith · job 75%sncro · job 74%amazon_mcp_server · job 74%mcp_screenshot_server · job 76%BrowserOps · job 73%chromedp_mcp · job 80%Browser Infrastructure for AI Agents · job 74%agentlimb · job 71%browser_mcp · job 79%pilotbrowsemcp · job 76%auto_browser · job 75%mcp_realbrowser · job 72%firefox_devtools_mcp · job 72%ProBrowser · job 71%drissionpage_mcp_server · job 77%ai_browser_mcp · job 75%mcp_pointer · job 71%drissionpage_mcp · job 77%glance · job 76%browserbuddy · job 76%melaya · job 75%SoftAuto · job 75%BunBrowser MCP · job 79%camofox_mcp · job 78%nodriver_mcp_server · job 78%pilot_mcp · job 77%humanized_browser · job 70%Brave DevTools MCP · job 76%opencode GUI Bridge · job 75%Browser Navigator MCP · job 75%AgentLock Browser · 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