Loading connector details…
Loading connector details…
Choose a unique username to continue using AgentHotspot
by llmsresearch • Uncategorized
An MCP server for automated generation and evaluation of academic diagrams and statistical plots from text descriptions.
Generate detailed academic methodology diagrams from textual descriptions.
Create statistical plots from CSV or JSON data with communicative intent.
Evaluate the quality of generated diagrams against human references using vision-language models.
PaperBanana provides an agentic multi-phase pipeline to generate publication-quality academic illustrations and statistical plots using multiple AI providers including OpenAI and Google Gemini. It supports input optimization, iterative refinement, batch processing, and user feedback integration. The MCP server exposes tools for generating diagrams, plots, and evaluating diagrams, enabling seamless integration with Claude Code, Cursor, or any MCP-compatible clients.
Generate a publication-quality methodology diagram from text. Args: source_context: Methodology section text or relevant paper excerpt. caption: Figure caption describing what the diagram should communicate. iterations: Number of refinement iterations (default 3). Returns: The generated diagram as a PNG image.
Generate a publication-quality statistical plot from JSON data. Args: data_json: JSON string containing the data to plot. Example: '{"x": [1,2,3], "y": [4,5,6], "labels": ["a","b","c"]}' intent: Description of the desired plot (e.g. "Bar chart comparing model accuracy"). iterations: Number of refinement iterations (default 3). Returns: The generated plot as a PNG image.
Evaluate a generated diagram against a human reference on 4 dimensions. Compares the model-generated image to a human-drawn reference using Faithfulness, Conciseness, Readability, and Aesthetics scoring with hierarchical aggregation. Args: generated_path: File path to the model-generated image. reference_path: File path to the human-drawn reference image. context: Original methodology text used to generate the diagram. caption: Figure caption describing what the diagram communicates. Returns: Formatted evaluation scores with per-dimension results and overall winner.
Scores are informational only and provided “as is” without warranty. AgentHotspot assumes no liability for actions taken based on these ratings.