thousand_api · job 81%dazbench · job 78%data-converter · job 79%pare · job 79%tools · job 82%ia-qa.com/mcp llm and RAG testing - Dev/QA toolbox · job 78%arch_tools · job 84%AgentScrape · job 81%nvm · job 79%joshua_wkl4_bristlecone_logic · job 86%Dumpling AI MCP Server · job 81%ai_netcafe · job 80%Botoi MCP · job 80%Model Context Protocol · job 78%Httpstatus MCP · job 78%jiebang_tools · job 84%Aipaygen · job 81%snipget · job 82%ultimate_mcp_server · job 83%documentize_mcp · job 80%toolsforagents · job 80%x402_tools · job 78%microapp_tools · job 83%sparkforge · job 81%hermes_plant · job 78%livedatalink · job 79%utilsforagents-mcp · job 84%apix420mcp1 · job 82%crawlforge-mcp · job 82%agentbits · job 82%GadgetHumans API Hub — 24 Free MCP Tools · job 83%APICK MCP · job 79%Terminalfeed · job 79%toolsnap_mcp · job 87%Frenchie · job 81%transform · job 78%Zambo AI Tools · job 81%sift_2 · job 78%toolkit_mcp_server · job 77%gemina · job 79%tinyfn · job 79%toolforte · job 81%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