MCP.Market

PaperBanana-CN MCP server

by mituan-ai·io.github.mituan-ai/paperbanana-cn·v2.0.1·82 stars
No reviews yet

Generate and evaluate academic diagrams and plots with independent model connections.

A92/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A92/100

full report

Adoption
Growing

82 stars

Reviews

Write one

Nobody has reviewed PaperBanana-CN yet.

If you have run it, two minutes of your experience saves the next person an afternoon.

PaperBanana-CN tools (11, 3 write)

write = sends, deletes, buys or posts

Read from the package source without running it. The installed server may list more.

  • batch_diagramswrite action

    Run methodology diagram batch from a manifest (YAML or JSON).

  • batch_plotswrite action

    Run statistical plot batch from a manifest (YAML or JSON).

  • continue_diagram

    Continue a methodology diagram run under ``output_dir`` / ``run_id``.

  • continue_plot

    Continue a statistical-plot run (same contract as ``continue_diagram``).

  • continue_runwrite action

    Continue refinement for a previous diagram or plot run (CLI: ``generate --continue-run``).

  • download_references

    Download the PaperBananaBench reference set.

  • evaluate_diagram

    Evaluate a generated diagram against a human reference on 4 dimensions.

  • evaluate_plot

    Evaluate a generated statistical plot against a human reference on 4 dimensions.

  • generate_diagram

    Generate a publication-quality methodology diagram from text.

  • generate_plot

    Generate a publication-quality statistical plot from JSON data.

  • orchestrate_figures

    Plan and optionally generate a multi-figure publication package from a paper.

Public scan report

scanner v0.1.9 · 2026-09-24 · same rubric, same numbers if you re-run it

no findings
  • Code scan132 source files scanned25/25
  • –Live reliabilityno gateway calls yet and no remote to proben/a
  • –Tool poisoningtools not inspected (local package is not executed); not countedn/a
  • Auth qualitylocal package, no credentials required12/15
  • Maintenancelast push 1 days ago15/15
  • Maintainer identityregistry namespace matches repository owner; GitHub account older than a year8/10
Overall 92/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How PaperBanana-CN compares

Against every graded AI and agents MCP server, from our own scans and uptime checks. Updated after each scan run.

Safety score
92/100
higher than 90% of 4,460 AI and agents servers
Tools
11
the typical AI and agents server has 6
Tools that change things
27%
typical: 0%. Fewer write tools means less an agent can break
GitHub stars
82
more than 93% of 2,711 AI and agents servers

What its tools let an agent do: 4 read · 2 create · 3 change · 2 run or deploy

Install PaperBanana-CN in Claude Code, Cursor or VS Code

claude mcp add paperbanana-cn -- uvx paperbanana-cn
Add to Cursor

What the publisher says

From the PaperBanana-CN repository's README, as published. We do not edit it. Read it on GitHub

<!-- mcp-name: io.github.mituan-ai/paperbanana-cn -->

English · 简体中文

<img src="https://raw.githubusercontent.com/mituan-ai/PaperBanana-CN/main/assets/readme/hero.webp" width="100%" alt="PaperBanana-CN scientific figure workbench with a generated multimodal fault-diagnosis figure"

PaperBanana-CN generates methodology diagrams from research descriptions and statistical plots from CSV or JSON data. It uses the PaperBanana scientific workflow and adds separate VLM and image-service connections, a Chinese Studio interface, and explicit aspect-ratio and resolution controls.

One run from input to figure

<img src="https://raw.githubusercontent.com/mituan-ai/PaperBanana-CN/main/assets/readme/studio-workflow.gif" width="960" alt="A PaperBanana-CN Studio run progressing from configured inputs to a completed scientific figure"

The recording follows a methodology-diagram run from submitted inputs to the completed result.

Before you start

You need Python 3.10-3.12, uv, and a desktop browser.

Each connection specifies its own protocol, Base URL, API key, model name, and timeout. The VLM and image roles may use the same service or two different services.

Quick start

1. Launch Studio

uvx paperbanana-cn studio

Open . uvx runs the package in an isolated environment and does not modify Debian or Ubuntu's system Python.

2. Add the model connections

Open Settings → VLM connection, fill in the service fields, and select Save and use. Repeat under Image connection before generating a methodology diagram.

Editing a saved connection does not activate it. An empty API-key field keeps the stored key. Studio does not fill stored keys back into the browser.

Connection manager screenshot and protocol notes

<img src="https://raw.githubusercontent.com/mituan-ai/PaperBanana-CN/main/assets/readme/connections-zh.webp" width="100%" alt="PaperBanana-CN connection manager with separate fields for a VLM service"

The connection guide lists the supported protocols, credential storage rules, connection tests, and legacy mode.

3. Generate a figure

Open Methodology diagram, provide the method content and figure caption, then choose an aspect ratio, resolution, and output format.

The same task from the CLI:

Shortened. The full README is on GitHub.

Nothing above is checked by us. What we check is on the safety report.

PaperBanana-CN: common questions

Is PaperBanana-CN MCP server safe?
Yes, by our scan: it is graded A (92/100). Read the PaperBanana-CN safety report
How do I install PaperBanana-CN?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does PaperBanana-CN need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is PaperBanana-CN maintained?
The last commit was 41 days ago (2026-09-24). The latest release is v2.0.1.
What can I use instead of PaperBanana-CN?
Servers from other publishers that do the same job: PaperBanana MCP server, Agent-Native Slides MCP server and VisualTorch MCP server.
How does PaperBanana-CN compare with other AI and agents MCP servers?
safety score 92/100 (higher than 90% of 4,460 AI and agents servers); tools 11 (the typical AI and agents server has 6); tools that change things 27% (typical: 0%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to PaperBanana-CN

Same job from other publishers: the closest match first, then the best rated.

  • PaperBanana
    Generate academic diagrams and statistical plots from text using multi-agent AI.
    A
  • Agent-Native Slides
    Agent-Native Google Slides - generate and edit React presentations
    More from BuilderIO →
    A
  • VisualTorch
    Render PyTorch architecture diagrams and animated GIF reveals from trusted model source.
    A
  • Openflowkit
    Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.
    A