marketflux-mcp · job 74%filing-intelligence · job 72%secant-agent-research-pack · job 72%tako · job 78%octagon · job 81%Tavily Search · job 76%factiq_plugin · job 73%hiro · job 73%agentql_mcp · job 75%deepkpi_mcp · job 79%scrape-agent-mcp · job 73%perplexity_search · job 73%oculo · job 71%you_com_mcp · job 74%XBRL US Filing Repository · job 72%mcp_massive · job 72%clawfetch_mcp · job 80%web_researcher_mcp · job 77%fmp_mcp_server_2 · job 76%rival_search_mcp · job 80%wisesheets · job 74%wigolo · job 79%investor_agent · job 78%jina_mcp_server · job 78%librecrawl_mcp · job 74%crw · job 78%swarm_web_crawller · job 77%finlight · job 76%firecrawl_mcp_multiple_keys · job 74%unquant · job 76%anakin · job 81%manawa_terminal · job 81%WebVector · job 76%Infobroker · job 73%Nimrod · job 74%AI Research Agent · job 71%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