mcp · handle multi_search_mcp · source page
Parallel Web Search · job 76%Serper Search and Scrape · job 75%GroundRoute: Web Search for AI Agents across 6 Engines ($10 free credit) · job 76%ryxell agent search · job 73%yandex · job 72%beacon_mcp · job 77%DeepSeek Search MCP · job 75%open_websearch · job 80%Free Web Search MCP · job 77%Knowledge Raven · job 74%MCP Server Web Search · job 81%web_search_mcp · job 82%mcp_gemini_google_search · job 76%mcp_local_rag · job 75%web_search_mcp_2 · job 85%scrapeunblocker_mcp · job 76%simple_websearch_mcp · job 74%talordata_mcp · job 79%zai_web_search_mcp · job 73%agent_web_search_mcp · job 77%MCP WebSearch Server · job 84%search-gateway · job 80%Smart Web Search MCP · job 79%Google SERP API · job 75%Brave MCP Server · job 76%SearchHub · job 76%DeepSeek Web Search MCP · job 79%Google Scrape MCP · job 76%brave-search · job 77%agentwebsearch_mcp · job 70%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