aimnis · job 70%Jina AI · job 75%agentwebsearch_mcp · job 75%serphouse_mcp · job 72%mcp_server_serper · job 74%Tavily Search · job 71%scrap_mcp · job 73%web_search_mcp · job 79%websearch_mcpserver · job 79%open_websearch · job 81%ryxell agent search · job 75%local · job 74%onion_search_mcp · job 78%web_forager · job 78%you_com_mcp · job 74%talordata_mcp · job 77%reefapi · job 74%steadyfetch · job 72%mcp_server_browserbase · job 74%Blopus · job 85%mcp_local_rag · job 77%mcp_gemini_google_search · job 73%firecrawl_mcp_multiple_keys · job 72%agent_web_search_mcp · job 71%beacon_mcp · job 77%exa_mcp_rotate · job 77%web_search_mcp_2 · job 74%catchall · job 73%mediawiki_mcp_server_2 · job 78%worbrow · job 78%mcp-retrieval · job 77%Nimrod · job 76%serper_mcp_server · job 74%pplx_custom_mcp · job 75%serpdive · job 80%ddgs · job 74%scrapegraph_mcp · job 73%SearXNG MCP Server · job 76%MCP WebSearch Server · job 76%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