Model Context Protocol · job 78%jiebang_tools · job 84%Zambo AI Tools · job 81%microapp_tools · job 83%snipget · job 82%sparkforge · job 81%tinyfn · job 79%toolforte · job 81%utilsforagents-mcp · job 84%Botoi MCP · job 80%pare · job 79%joshua_wkl4_bristlecone_logic · job 86%agentbits · job 82%toolsnap_mcp · job 87%toolsforagents · job 80%documentize_mcp · job 80%arch_tools · job 84%GadgetHumans API Hub — 24 Free MCP Tools · job 83%ultimate_mcp_server · job 83%ia-qa.com/mcp llm and RAG testing - Dev/QA toolbox · job 78%data-converter · job 79%tools · job 82%Tanod · job 85%APIStack MCP Servers · job 84%ConvertFileFast MCP Server · job 83%thousand_api · job 81%Httpstatus MCP · job 78%Frenchie · job 81%Sample MCP Server · job 80%sitecheck · job 83%datcontext · job 82%agent_tools_uk · job 82%Node.js MCP Server · job 80%MCP Tools Lab · job 85%doc_convert_mcp · job 79%ALICE V0 MCP · job 79%tidydata_tools · job 80%cofferdock · job 80%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