# PaperBanana CN

> Scientific figure workbench with independent VLM/image connections, Chinese UI, and unified size controls.

- **Type:** MCP server
- **Install:** `agentstack add mcp-mituan-ai-paperbanana-cn`
- **Verified:** Yes — security-reviewed for prompt injection and unsafe behavior
- **Seller:** [mituan-ai](https://agentstack.voostack.com/s/mituan-ai)
- **Installs:** 0
- **Category:** [Content & Media](https://agentstack.voostack.com/c/content-and-media)
- **Latest version:** 0.1.0
- **License:** MIT
- **Upstream author:** [mituan-ai](https://github.com/mituan-ai)
- **Source:** https://github.com/mituan-ai/PaperBanana-CN
- **Website:** https://github.com/mituan-ai/PaperBanana-CN

## Install

```sh
agentstack add mcp-mituan-ai-paperbanana-cn
```

Requires the [AgentStack CLI](https://agentstack.voostack.com/docs/cli). Works with Claude Code, Cursor, and any MCP-compatible agent.

## About

English ·
  简体中文

  

  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

  

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](https://docs.astral.sh/uv/), and a desktop browser.

| Task | Required model connections |
|---|---|
| Methodology diagram | VLM and image generation |
| Statistical plot | VLM only |
| Multi-panel composition and run browsing | None |

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

```bash
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

  

The [connection guide](https://github.com/mituan-ai/PaperBanana-CN/blob/main/docs/CONNECTIONS.md)
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:

```bash
paperbanana-cn generate \
  --input method.txt \
  --caption "Overview of the proposed architecture" \
  --aspect-ratio 16:9 \
  --resolution 2K \
  --format png
```

## What PaperBanana-CN adds

### Separate VLM and image connections

The two model roles have independent protocol, Base URL, API key, model, and timeout settings.
Studio, CLI, and MCP resolve the same saved connections. Saved profiles contain credential
references; API keys remain outside the repository and run metadata.

Official APIs, OpenAI-compatible services, and Gemini-compatible services are supported. Provider
specifics stay in the adapters rather than the scientific workflow.

### Chinese and English Studio

The Studio interface, help text, validation, progress messages, and errors are available in Chinese
and English. Changing the interface language does not rewrite prompts, paper text, or labels inside
the generated figure.

### Aspect ratios and resolution

Supported aspect ratios:

`1:1` · `4:3` · `3:2` · `5:4` · `16:9` · `21:9` · `4:5` · `3:4` · `2:3` · `9:16`

Resolution tiers:

`1K` · `2K` · `4K`

Studio shows the request size or provider-native tier before generation. If an adapter cannot
produce the selected combination, validation stops the request and reports the unsupported option.

## Studio workflows

| Area | Workflow | Model connections |
|---|---|---|
| Create | Methodology diagram | VLM and image |
| Create | Statistical plot | VLM |
| Improve | Continue a saved run | Depends on the saved run |
| Improve | Quality evaluation | VLM |
| Automate | Full-paper orchestration | VLM and image |
| Automate | Batch generation | Depends on the task type |
| Automate | Parameter sweep | VLM and image |
| Tools | Multi-panel composition | None |
| Tools | Run browser | None |

  

Methodology-diagram workspace

  

Statistical-plot workspace using synthetic demonstration data

## CLI, MCP, Docker, and Colab

| Entry point | Command or link |
|---|---|
| Studio | `paperbanana-cn studio` |
| CLI | `paperbanana-cn generate --help` |
| MCP server | `paperbanana-cn mcp` |
| GitHub Action | [Action reference](https://github.com/mituan-ai/PaperBanana-CN/blob/main/integrations/github-action/README.md) |
| Docker | `ghcr.io/mituan-ai/paperbanana-cn:2.0.1` |
| Colab | [Quickstart notebook](https://colab.research.google.com/github/mituan-ai/PaperBanana-CN/blob/main/notebooks/PaperBanana_CN_Quickstart.ipynb) |

MCP client configuration

```json
{
  "mcpServers": {
    "paperbanana-cn": {
      "command": "uvx",
      "args": ["paperbanana-cn", "mcp"]
    }
  }
}
```

The server provides 11 tools and reads the same active connections as Studio and CLI. See the
[MCP guide](https://github.com/mituan-ai/PaperBanana-CN/blob/main/mcp_server/README.md) for the tool
list and arguments.

Docker

```bash
docker run --rm -p 7860:7860 \
  -v paperbanana-cn-config:/home/paperbanana/.config/paperbanana-cn \
  -v paperbanana-cn-data:/home/paperbanana/.local/share/paperbanana-cn \
  -v paperbanana-cn-outputs:/work/outputs \
  ghcr.io/mituan-ai/paperbanana-cn:2.0.1 \
  studio --host 0.0.0.0
```

Permanent install, source setup, and optional providers

Install the command in a uv-managed environment:

```bash
uv tool install paperbanana-cn
paperbanana-cn studio
```

Run the current source checkout:

```bash
git clone https://github.com/mituan-ai/PaperBanana-CN.git
cd PaperBanana-CN
uv sync
uv run paperbanana-cn studio
```

The default package includes Studio, MCP, PDF input, OpenAI-compatible services, and Gemini.

| Optional adapter | Install |
|---|---|
| AWS Bedrock | `uv tool install "paperbanana-cn[bedrock]"` |
| Anthropic | `uv tool install "paperbanana-cn[anthropic]"` |
| LiteLLM | `uv tool install "paperbanana-cn[litellm]"` |
| All optional providers | `uv tool install "paperbanana-cn[all-providers]"` |

For CI, use `paperbanana-cn connections add --api-key-env ENV_VAR` so the key is read from an
environment variable instead of a command-line value.

## V1 and upstream

V2 is maintained on `main` as the `paperbanana-cn` distribution, the `paperbanana_cn` Python
module, and the `paperbanana-cn` command.

- [Browse the frozen `v1` branch](https://github.com/mituan-ai/PaperBanana-CN/tree/v1)
- [Download the `v1.0.0` release](https://github.com/mituan-ai/PaperBanana-CN/releases/tag/v1.0.0)

The scientific figure-generation core is based on
[`llmsresearch/paperbanana`](https://github.com/llmsresearch/paperbanana). PaperBanana-CN is an
unofficial community implementation and is not affiliated with or endorsed by the upstream
authors.

## Community

PaperBanana-CN is maintained by [mituan](https://github.com/mituan-ai) under the
[MIT License](https://github.com/mituan-ai/PaperBanana-CN/blob/main/LICENSE).

- Ask usage questions in [Discussions](https://github.com/mituan-ai/PaperBanana-CN/discussions).
- Report reproducible bugs in [Issues](https://github.com/mituan-ai/PaperBanana-CN/issues).
- Report vulnerabilities through [Private Vulnerability Reporting](https://github.com/mituan-ai/PaperBanana-CN/security/advisories/new).
- Read [CONTRIBUTING.md](https://github.com/mituan-ai/PaperBanana-CN/blob/main/CONTRIBUTING.md) before opening a pull request.

Development checks

```bash
git clone https://github.com/mituan-ai/PaperBanana-CN.git
cd PaperBanana-CN
uv sync --extra dev
uv run pytest tests/ -q
uv run ruff check paperbanana_cn/ mcp_server/ tests/ scripts/
```

Do not upload API keys, private relay URLs, unpublished papers, private datasets, local connection
stores, or generated run directories.

## Star history

## Source & license

This open-source MCP server is cataloged on AgentStack and links to its original source — we do not rehost the code.

- **Author:** [mituan-ai](https://github.com/mituan-ai)
- **Source:** [mituan-ai/PaperBanana-CN](https://github.com/mituan-ai/PaperBanana-CN)
- **License:** MIT
- **Homepage:** https://github.com/mituan-ai/PaperBanana-CN

Install and usage instructions live in the source repository linked above.

## Pricing

- **Free** — Free

## Security capabilities

Automated source analysis of v0.1.0 — what this tool can access:

- **Network access:** no
- **Filesystem access:** no
- **Shell / process execution:** no
- **Environment & secrets:** no
- **Dynamic code execution:** no

*"Yes" means the capability is present in the source — more access means more to trust, not that it is unsafe.*


## Versions

- **0.1.0** — security scan: passed — Imported from the upstream source.

## Links

- Listing page: https://agentstack.voostack.com/l/mcp-mituan-ai-paperbanana-cn
- Seller: https://agentstack.voostack.com/s/mituan-ai
- Browse the marketplace: https://agentstack.voostack.com/browse

---
Listed on AgentStack — the marketplace for AI agent skills and MCP servers. Every listing is security-reviewed. Creators keep 70%.