MCP.Market

VisualTorch MCP server

by willyfh·io.github.willyfh/visualtorch·v1.4.1·346 stars
No reviews yet

Render PyTorch architecture diagrams and animated GIF reveals from trusted model source.

A86/100grade A
Write a reviewInstall
What users say
No reviews yet
Be the first
Safety scan
A86/100

full report

Adoption
Established

346 stars277 downloads/wk

Reviews

Write one

Nobody has reviewed VisualTorch yet.

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

VisualTorch tools (4)

write = sends, deletes, buys or posts

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

  • animate_model

    Render a trusted PyTorch model source as an animated VisualTorch GIF.

  • visualize_model

    Render a trusted PyTorch model source as a static VisualTorch PNG.

  • visualtorch_capabilities

    Return structured styles, options, palettes, output contracts, and safety constraints.

  • visualtorch_reference

    Return canonical upstream VisualTorch documentation links for all or one style.

Public scan report

scanner v0.1.10 · 2026-11-05 · same rubric, same numbers if you re-run it

1 medium
  • Code scan24 source files scanned20/25
  • –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 year9/10

Findings (1)

  • mediumeval / new Function usedexec.eval
    visualtorch-1.4.1/visualtorch_mcp/worker.py: … raise TypeError(message) model = eval(model_expression, namespace) # noqa: S3…
Overall 86/100. Components that don't apply are left out of the denominator. Any critical finding is an F.RubricAppeal a findingJSON

How VisualTorch compares

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

Safety score
86/100
higher than 77% of 4,456 AI and agents servers
Tools
4
the typical AI and agents server has 7
Tools that change things
0%
typical: 3%. Fewer write tools means less an agent can break
GitHub stars
346
more than 95% of 2,733 AI and agents servers
Downloads a week
277
more than 80% of 1,712 AI and agents servers with a package

What its tools let an agent do: 4 read

Install VisualTorch in Claude Code, Cursor or VS Code

claude mcp add visualtorch -- uvx visualtorch
Add to Cursor

What the publisher says

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

VisualTorch aims to help visualize Torch-based neural network architectures. It currently supports generating flow-style, graph-style, and LeNet-style architectures for PyTorch Sequential and Custom models. Its original visual styles were inspired by visualkeras, pytorchviz, pytorch-summary, and torchview; since then, it has grown its own unified tracing backend and architecture-handling logic well beyond its origins.

Note: 1.0+ is a major release with breaking API changes, but with significantly better features and algorithms - upgrading is recommended. For the old API, use 0.2.5 or older.

Limitation: VisualTorch traces a real forward pass to build the diagram, which has an inherent limitation shared by any tracing-based approach (not a bug, and not fixable without full symbolic execution): models with data-dependent control flow (e.g. a branch only taken if a tensor value crosses some threshold) only show whichever branch the traced dummy input happened to take. Separately, a layer that returns multiple meaningful output tensors (e.g. a custom multi-task head, or nn.LSTM's (output, (hn, cn))) still has its node's size based on only its first tensor; with show_dimension=True, every output tensor's shape is shown in the label, not just the first. Downstream connections are correct either way. Contributions are welcome!

Animated Reveal

Every style can also render as an animated GIF, revealing the model one layer/column at a time, via visualtorch.animate(model, input_shape, style=...) - see it in action for flow, graph, and lenet styles.

Documentation

Online documentation is available at visualtorch.readthedocs.io.

The docs include usage examples, API references, and other useful information.

Installation

See the Installation page.

MCP integration

Shortened. The full README is on GitHub.

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

VisualTorch: common questions

Is VisualTorch MCP server safe?
Yes, by our scan: it is graded A (86/100). Read the VisualTorch safety report
How do I install VisualTorch?
It runs on your machine. Copy the Claude Code, Cursor, VS Code or Claude Desktop config from the install section.
Does VisualTorch need an API key?
Not as far as the registry entry and our scan can tell: no credentials are declared or required.
Is VisualTorch maintained?
The last commit was 11 days ago (2026-11-05). The latest release is v1.4.1.
What can I use instead of VisualTorch?
Servers from other publishers that do the same job: Openflowkit MCP server, Agent-Native Plan MCP server and PaperBanana MCP server.
How does VisualTorch compare with other AI and agents MCP servers?
safety score 86/100 (higher than 77% of 4,456 AI and agents servers); tools 4 (the typical AI and agents server has 7); tools that change things 0% (typical: 3%. Fewer write tools means less an agent can break). Full comparison.

Alternatives to VisualTorch

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

  • Openflowkit
    Architecture diagrams for your agent: draw on the live OpenFlowKit canvas or edit diagram files.
    A
  • Agent-Native Plan
    Structured visual plans and PR recaps with diagrams, prototypes, annotations, and sharing
    A
  • PaperBanana
    Generate academic diagrams and statistical plots from text using multi-agent AI.
    A
  • Persome
    Local-first personal memory and model server for trusted MCP agents on macOS.
    A
  • three.ws Avatars
    three.ws 3D avatars in your agent: render a live, interactive 3D avatar inline, or get an embed.
    More from nirholas →
    A
VisualTorch vs Openflowkit