PaperBanana-CN

Install

Works with Claude Code, Codex, VS Code, Cursor, Windsurf, Claude Desktop. Read the repository before you give any tool access to your data.

npx agentmarket install connector/mituan-ai-paperbanana-cn

About

No reviews yet. Installed it? Reviews come from verified installers only. How reviews work

Permissions

What this server can do and what it asks for, from its tool list and install config. Checked Oct 25, 2026.

Tools

3 read · 4 write · 0 delete · 4 not yet classified

Secrets

None asked for

Install scripts

Not scanned yet

Runs as

Python package

Tools (11)

Read from the source code; the running server may differ. Descriptions are the server’s own words; hidden characters are shown as [U+…].

• batch_diagrams

  Run methodology diagram batch from a manifest (YAML or JSON). Each manifest item needs ``input`` (text or PDF path) and ``caption``. Paths are resolved relative to the manifest file directory. Returns JSON with ``batch_dir``, ``batch_report_path``, per-item summary, ``composite_path`` when configured, and ``strict_success`` (false if any item failed).

• batch_plots

  Run statistical plot batch from a manifest (YAML or JSON). Each item needs ``data`` (CSV or JSON path) and ``intent``. When ``vlm_provider`` is omitted, defaults to ``gemini`` (same as CLI plot-batch). Returns JSON with ``batch_dir``, ``batch_report_path``, item summary, and ``strict_success``.

• continue_diagram

  Continue a methodology diagram run under ``output_dir`` / ``run_id``. Loads ``run_input.json`` and the latest iteration from an existing ``run_*`` directory (same as ``paperbanana-cn generate --continue-run``). Runs more visualizer–critic rounds without redoing retrieval / planner / stylist. Args: run_id: Directory name (e.g. ``run_20250109_120000_abc``). output_dir: Base output directory containing the run folder. feedback: Optional notes for the critic (same as CLI ``--feedback``). iterations: Extra refinement rounds when ``auto_refine`` is false; also sets ``refine…

• continue_plot

  Continue a statistical-plot run (same contract as ``continue_diagram``). Use when ``run_input.json`` has ``diagram_type`` ``statistical_plot``.

• continue_run

  Continue refinement for a previous diagram or plot run (CLI: ``generate --continue-run``). Loads state from ``<output_dir>/<run_id>/`` (default ``outputs/`` from settings), then runs additional visualizer/critic iterations in the same run directory. Optional ``feedback`` is passed to the critic, matching ``--feedback`` on the CLI. Args: run_id: Directory name of the run (e.g. ``run_20260218_125448_e7b876`` under ``outputs/``). feedback: Optional user notes for the critic (layout, labels, style). iterations: Extra refinement iterations when ``auto_refine`` is False (default 3). …

• download_references

  Download the PaperBananaBench reference set. Downloads ~254 MB of reference diagrams (~298 examples) from the project-hosted GitHub release mirror (SHA256-verified) and caches them locally. The Retriever agent uses these for better in-context learning during diagram generation. Only needs to be run once — subsequent calls detect the cached data and return immediately. Use force=True to re-download. Args: force: Re-download even if already cached. Returns: Status message with cache location and example count.

• evaluate_diagram

  Evaluate a generated diagram against a human reference on 4 dimensions. Compares the model-generated image to a human-drawn reference using Faithfulness, Conciseness, Readability, and Aesthetics scoring with hierarchical aggregation. Args: generated_path: File path to the model-generated image. reference_path: File path to the human-drawn reference image. context: Original methodology text used to generate the diagram. caption: Figure caption describing what the diagram communicates. Returns: Formatted evaluation scores with per-dimension results and overall winner.

• evaluate_plot

  Evaluate a generated statistical plot against a human reference on 4 dimensions. Args: generated_path: File path to the model-generated plot. reference_path: File path to the human reference plot. data_json: JSON string containing the source data used to generate the plot. intent: Communicative intent used for plot generation. Returns: Formatted evaluation scores with per-dimension results and overall winner.

• generate_diagram

  Generate a publication-quality methodology diagram from text. Args: source_context: Methodology section text or relevant paper excerpt. caption: Figure caption describing what the diagram should communicate. iterations: Number of refinement iterations (default 3, used when auto_refine=False). aspect_ratio: Target aspect ratio. Supported: 1:1, 4:3, 3:2, 5:4, 16:9, 21:9, 4:5, 3:4, 2:3, 9:16. optimize: Enrich context and sharpen caption before generation (default True). Set False to skip preprocessing for faster results. auto_refine: Let critic loop until …

• generate_plot

  Generate a publication-quality statistical plot from JSON data. Args: data_json: JSON string containing the data to plot. Example: '{"x": [1,2,3], "y": [4,5,6], "labels": ["a","b","c"]}' intent: Description of the desired plot (e.g. "Bar chart comparing model accuracy"). iterations: Number of refinement iterations (default 3, used when auto_refine=False). aspect_ratio: Target aspect ratio. Supported: 1:1, 4:3, 3:2, 5:4, 16:9, 21:9, 4:5, 3:4, 2:3, 9:16. optimize: Enrich context and sharpen caption before generation (default True). Set False to skip p…

• orchestrate_figures

  Plan and optionally generate a multi-figure publication package from a paper. Mirrors ``paperbanana-cn orchestrate``. Use ``dry_run=True`` to write ``orchestration_plan.json`` only (no API generation). For continuation, pass ``resume_orchestrate`` with an orchestration id or package directory path. Returns: JSON string with orchestration_id, paths to ``figure_package.json``, ``figures.tex``, ``captions.md``, ``orchestration_plan.json``, counts, ``strict_success``, and ``failures`` when applicable.

Signals

Stars

84

Forks

5

Open issues

0

Contributors

36

Weekly downloads

19

Last commit

Jul 24, 2026 (3 months ago)

Last release

Jul 24, 2026 (3 months ago)

Last package publish

Jul 24, 2026 (3 months ago)

From GitHub (fetched Oct 24, 2026) and the package registry.

Details

Registry name

io.github.mituan-ai/paperbanana-cn

Version

2.0.1

Auth

No auth

Packages

pypi paperbanana-cn

License

MIT

Repository

github.com/mituan-ai/PaperBanana-CN

Website

github.com/mituan-ai/PaperBanana-CN

First seen

Oct 24, 2026

Last checked

Oct 24, 2026

Source

Official MCP Registrygithub-graphql