PaperBanana — Claude Code MCP server: what it does, how to install
Creates publication-ready academic diagrams and statistical plots from text descriptions using a multi-agent workflow.
claude mcp add paperbanana -- uvx paperbananaWhat PaperBanana does
PaperBanana converts technical descriptions of algorithms and architectures into visual assets for research papers. It runs a two-phase agentic pipeline that generates diagrams and refines them across iterations. The server integrates with several model providers: Google Gemini, OpenAI, Azure OpenAI, and Atlas Cloud.
The framework handles batch tasks using YAML or JSON manifests and can render statistical charts straight from CSV tables. It also ingests methodology sections from PDF files with page-level selection powered by PyMuPDF.
Generating figures requires an active API key from Google Gemini, OpenAI, or Atlas Cloud. Local execution also depends on Python 3.10 or newer.
What it helps with
- generate academic system diagrams from methodology descriptions
- render batches of statistical figures from CSV data and JSON manifests
- extract paper context from specific PDF pages to guide diagrams
- refine generated illustrations iteratively with agentic feedback
Example prompts for the agent
- Generate an architecture diagram based on the description in
method.txt. - Create statistical plots from the manifest
manifest.yamlusing input CSVs. - Evaluate and refine the generated figure according to review notes.
How to install PaperBanana
Platform CLI
claude mcp add paperbanana -- uvx paperbananauvx runs the command named after the package; if the README names another one, use uvx --from paperbanana <command>
Platform CLI
codex mcp add paperbanana -- uvx paperbananauvx runs the command named after the package; if the README names another one, use uvx --from paperbanana <command>
Config file
{
"mcpServers": {
"paperbanana": {
"command": "uvx",
"args": [
"paperbanana"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from paperbanana <command>
Config file
{
"servers": {
"paperbanana": {
"type": "stdio",
"command": "uvx",
"args": [
"paperbanana"
]
}
}
}uvx runs the command named after the package; if the README names another one, use uvx --from paperbanana <command>
Platform CLI
gemini mcp add paperbanana uvx paperbananauvx runs the command named after the package; if the README names another one, use uvx --from paperbanana <command>
Step by step, with commands for each platform: How to add an MCP server to Claude Code, Codex, Cursor, VS Code, Gemini CLI and more
Questions about PaperBanana
How do I install PaperBanana in Claude Code?
Run claude mcp add paperbanana -- uvx paperbanana in your terminal. You need uv installed along with an API key for your chosen provider.
What does PaperBanana do?
It gives your AI coding assistant tools to produce publication-grade diagrams and statistical plots from text prompts or research notes.
Which model providers are supported?
It supports Google Gemini, OpenAI (including GPT-Image-1.5), Azure OpenAI Foundry endpoints, and Atlas Cloud.
