PaperBanana is an agentic framework for generating publication-quality academic diagrams and statistical plots from text descriptions, supporting multiple AI providers. It allows batch generation of diagrams and plots from manifest files.
From the registry: Generate academic diagrams and statistical plots from text using multi-agent AI.

$ pip install 'paperbanana[mcp]'https://pypi.org/project/paperbanana/Please install the `paperbanana` MCP server into my current AI client (that's you).
Required prerequisites (do these first if not already done):
- **LLM API Key** — OpenAI API key or Google Gemini API key (free tier available at Google AI Studio) (https://makersuite.google.com/app/apikey)
- **Install paperbanana with MCP extra** — Install the Python package Run: `pip install 'paperbanana[mcp]'` (https://pypi.org/project/paperbanana/)
Canonical MCP server config (stdio transport):
- command: `uvx`
- args: ["--from","paperbanana[mcp]","paperbanana-mcp"]
- optional environment variables:
- `GOOGLE_API_KEY`: Google Gemini API key (free tier) (example: `<your-google-api-key>`)
- `OPENAI_API_KEY`: OpenAI API key (example: `<your-openai-api-key>`)
Note: Unofficial open-source implementation of PaperBanana paper (arXiv:2601.23265). 3 MCP tools: generate_diagram, generate_plot, evaluate_diagram. Requires OpenAI or Google Gemini API key. Python 3.10+ required.
Add this MCP server to my current client's config in the correct format for you. If you need secrets or credentials I haven't provided, ASK me — do not invent values or leave raw placeholders. After adding it, tell me how to verify the server is connected.OPENAI_API_KEYrequiredAPI key for OpenAI services.GOOGLE_API_KEYrequiredAPI key for Google Gemini services.OPENAI_BASE_URLBase URL for Azure OpenAI / Foundry endpoints.GOOGLE_BASE_URLBase URL for Gemini-compatible gateways.