mcp · handle web_search_mcp_2 · source page
multi_search_mcp · job 85%talordata_mcp · job 81%tavily_mcp · job 82%Tavily · job 81%brave_search_mcp_server · job 76%pixserp · job 75%ryxell agent search · job 81%web_search · job 80%web_search_mcp · job 82%open_websearch · job 80%agent_web_search_mcp · job 79%aimnis · job 72%one_search_mcp · job 80%serphouse_mcp · job 74%anysearch · job 76%GroundRoute: Web Search for AI Agents across 6 Engines ($10 free credit) · job 77%webfetch_mcp · job 74%search-gateway · job 82%websearch-ring · job 76%SearchHub · job 77%brave-search · job 85%Brave MCP Server · job 80%worbrow · job 75%cyxj_groksearch · job 74%Parallel Web Search · job 80%agentwebsearch_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