mcp · handle aigc_radar
sophotron · job 73%Google Scholar MCP · job 75%paperclip_2 · job 79%google_scholar_mcp · job 75%scientific_papers_mcp · job 73%AI Agent Index · job 72%Harpd Agent API · job 73%scholar_search_mcp · job 80%AI Agent Store · job 73%research_mcp · job 74%CORE Research MCP · job 78%bgpt_mcp · job 78%aidemos_mcp · job 73%Grandpa's AI · job 74%context_awesome · job 79%arxiv_reader_mcp · job 78%DeepResearch MCP Server · job 80%web_researcher_mcp · job 80%SciWeave MCP Server · job 76%Keyless Research MCP · job 78%datacenterindex · job 74%Academic Paper Search MCP Server · job 74%IA.med MCP · job 75%Sovereign AI Blog · job 76%PaperPilot · job 84%X-deepresearch · job 75%arxiv_mcp_server · job 80%OpenAbstracts · job 79%hfpaperwatch · job 77%ArXivLens MCP · job 83%AgentCrush · job 76%Knowledge Engine · job 80%Tool Directory MCP Server · job 78%Git for Me · 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