mcp · handle find_research_papers_mcp
paperclip_2 · job 84%pubcrawl · job 71%paper_search_mcp · job 77%semantic_scholar_graph_api · job 76%crossref_mcp_server · job 75%openalex_research_mcp · job 83%perplexity_search · job 75%web_researcher_mcp · job 81%arxiv-mcp-server · job 80%zotseek · job 70%pubmed_mcp_server · job 77%google_scholar_mcp · job 76%scientific_papers_mcp · job 86%paperpiggy · job 71%sophotron · job 75%scopus_mcp · job 82%openpapers_mcp · job 83%arxiv_reader_mcp · job 83%arxiv · job 87%arxiv_mcp_server · job 79%AI Research Assistant · job 89%scholar_search_mcp · job 88%pubmed_search_mcp_2 · job 82%autosearch · job 74%AI Research Assistant MCP · job 86%PaperPilot · job 85%Noodle Biomedical Literature Discovery MCP · job 82%SciWeave MCP Server · job 72%citeme · job 74%OpenPapers · job 74%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