MCP Tools DirectoryAbout this integration
Generate academic diagrams and statistical plots from text using multi-agent AI.
- Transport
- stdio
- Authentication
- api-key
- Initial setup
- credentials
- Runtime
- unattended
- Evidence
- documented
- Version
- 0.1.1
- Package
- paperbanana
- Last compatibility test
- Not independently tested
Connect your agent
paperbananaThis is an unofficial implementation of the cited research. Model calls can incur provider cost and transmit supplied content. No package, provider, or generated output was executed or evaluated.
Capabilities: Generate academic diagrams, Generate statistical plots, Continue prior generation runs, Evaluate diagrams and plots, Run batch and full-paper figure workflows
Connected profiles
Additional details
io.github.llmsresearch/paperbanana
Source ↗ · Checked 2026-09-170.1.1
Source ↗ · Checked 2026-09-17CC0-1.0; package licenses are separate
Source ↗ · Checked 2026-09-17pypi
Source ↗ · Checked 2026-09-17paperbanana
Source ↗ · Checked 2026-09-190.3.0
Source ↗ · Checked 2026-09-19The Python distribution declares a paperbanana-mcp console script, and the publisher documents a uvx stdio configuration using the mcp optional dependency.
Source ↗ · Checked 2026-09-19Generation requires a configured provider API key; the reviewed MCP example supplies GOOGLE_API_KEY, while the broader configuration also supports OpenAI and Atlas Cloud keys.
Source ↗ · Checked 2026-09-19The MCP client launches paperbanana-mcp over local stdio with uvx; the process then connects to the configured model and image-generation provider endpoints.
Source ↗ · Checked 2026-09-19Publisher documentation reviewed; package and integration endpoint not executed or independently security-audited.
Source ↗ · Checked 2026-09-19