{"id":"paperbanana","name":"PaperBanana","homepage":"https://github.com/llmsresearch/paperbanana","repo_url":"https://github.com/llmsresearch/paperbanana","category":"research-tools","subcategories":["academic-writing","diagram-generation","mcp-server"],"tags":["mcp","academic","diagrams","visualization","research","figures","openai","gemini","multiagent"],"what_it_does":"PaperBanana is an agentic framework and MCP server that generates publication-quality academic diagrams and statistical plots from text descriptions using a multi-agent pipeline with GPT or Gemini vision models, including iterative auto-refinement.","use_cases":["Generating methodology flowcharts and architecture diagrams for AI research papers from plain-text descriptions","Creating statistical plots and charts from CSV/JSON experimental results data","Auto-refining generated figures iteratively until a VLM critic deems them publication-ready","Integrating diagram generation directly into Claude Code or Cursor workflows via MCP"],"not_for":["Non-academic or marketing design work","Interactive or animated data visualization","Teams without OpenAI or Gemini API access and budget"],"best_when":"A researcher needs to produce polished methodology or results figures for a paper draft without manual design tools, and wants AI-driven iterative refinement.","avoid_when":"Cost of LLM API calls per diagram is prohibitive, or highly customized branding/style requirements exist.","alternatives":["diagrams-net","matplotlib","plotly","inkscape","napkin-ai"],"af_score":63.9,"security_score":60.0,"reliability_score":null,"package_type":"mcp_server","discovery_source":["github","mcp_registry"],"priority":"low","status":"evaluated","version_evaluated":"latest","last_evaluated":"2026-03-01T09:50:06.054879+00:00","performance":{"latency_p50_ms":null,"latency_p99_ms":null,"uptime_sla_percent":null,"rate_limits":null,"data_source":"llm_estimated","measured_on":null}}