amazon_mcp_server · job 74%mcp_screenshot_server · job 76%BrowserOps · job 73%chromedp_mcp · job 80%agentlimb · job 71%browser_agent_py · job 71%browseros · job 75%Kernel · job 72%AgentSmith · job 75%sncro · job 74%BunBrowser MCP · job 79%Browser Compat MCP Server · job 75%drissionpage_mcp · job 77%glance · job 76%browserbuddy · job 76%drissionpage_mcp_server · job 77%Browser Infrastructure for AI Agents · job 74%browser_mcp · job 79%ScrAPI MCP · job 73%Botcan · job 74%Selenium MCP Server · job 73%mcp_realbrowser · job 72%ai_browser_mcp · job 75%mcp_pointer · job 71%pilotbrowsemcp · job 76%auto_browser · job 75%firefox_devtools_mcp · job 72%humanized_browser · job 70%camofox_mcp · job 78%nodriver_mcp_server · job 78%pilot_mcp · job 77%ApplyOps · job 76%mcp-web · job 79%MCP Agent Playwright · job 78%Playwright MCP · job 78%Laya Browser MCP · job 81%Brave DevTools MCP · job 76%opencode GUI Bridge · job 75%MCP Browser Use · job 81%Invisible Playwright MCP · job 80%Web Agent MCP · job 79%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