VisualTorch

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

Connector by willyfh · GitHub account verified by the MCP Registry

IndexedMITLocal (stdio)★ 341

Chalk Labs

Need help deploying VisualTorch?

Chalk Labs sets up agents like this inside real teams: connected to your tools, tested on your data, with a human in the loop where it matters.

Book a call

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/willyfh-visualtorch

Asks which of your tools to add it to (Claude Code, Codex, Cursor, VS Code, Windsurf, Gemini CLI, Claude Desktop) and shows the change first. See https://agentmart.dev/cli.

Get the weekly diff

The weekly diff: one email a week with new agent tools, notable updates and grade changes, plus security alerts for tools you follow. Double opt-in, one-click unsubscribe.

About

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

Use cases: data-visualization, documentation

Reviews

Write a review

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 · 0 write · 0 delete · 1 not yet classified
Secrets: None asked for
Install scripts: None found
Runs as: Python package

Tools by what they do 4

Read from the source code; the running server may list different tools.

Read 3 · Look things up without changing anything.

visualize_model
visualtorch_capabilities
visualtorch_reference

Not yet classified 1 · We could not tell from the name and description.

animate_model

Files it touches

Any path the agent passes to its tools

Tools (4)

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

animate_model
Render a trusted PyTorch model source as an animated VisualTorch GIF. The model-source and input-shape contract matches visualize_model. Put animation controls in options: frame_duration and final_hold_duration are milliseconds, and loop is a boolean. visualtorch_capabilities reports their defaults and every style-specific option. This tool executes source code with the current user's permissions. It is process-separated for reliability, not sandboxed for security, so only provide source you trust. The returned object describes the GIF written to disk; it does not embed the animation bytes.
visualize_model
Render a trusted PyTorch model source as a static VisualTorch PNG. The source must define the model and any classes it needs. By default the worker evaluates ``model_expression="model"`` after executing source; use an expression such as ``Net()`` or ``build_model()`` when source defines a class or factory. Input shape includes the batch dimension and may be one shape or a list of shapes for a multi-input model. This tool executes source code with the current user's permissions. It is process-separated for reliability, not sandboxed for security, so only provide source you trust. The returned…
visualtorch_capabilities
Return structured styles, options, palettes, output contracts, and safety constraints. Supply a canonical style or alias to limit the styles section, or omit it for the complete VisualTorch MCP capability manifest.
visualtorch_reference
Return canonical upstream VisualTorch documentation links for all or one style.

Compare and alternatives

Alternatives to VisualTorch →

Featured in

Signals

Stars: 341
Forks: 20
Open issues: 3
Contributors: 14
Weekly downloads: 578
Last commit: Oct 16, 2026 (15 days ago)
Last release: Jul 28, 2026 (3 months ago)
Last package publish: Jul 28, 2026 (3 months ago)

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

Details

Registry name: io.github.willyfh/visualtorch
Version: 1.4.1
Auth: No auth
Packages: pypi visualtorch
License: MIT
Repository: github.com/willyfh/visualtorch
Website: visualtorch.readthedocs.io/en/latest/markdown/get_started/mcp.html
First seen: Oct 24, 2026
Last checked: Oct 24, 2026
Source: Official MCP Registry github-graphql

Done for you

Rather not set it up yourself?

Chalk Labs scopes, builds and runs agents for your team: the task audit, the eval harness, the integrations and the weekly ops report. Fixed scope, priced before we start.

See how we build AI agents →Read the case studies

Chalk Labs is a two-founder AI and growth studio. We build AI agents, CRMs and MVPs for Web3 and AI companies, and have shipped 50+ product and token launches.

launches shipped: 50+; launches shipped
media placements: 500+; media placements
founders on every account: 2; founders on every account

Press we've placed: Forbes · CoinDesk · Decrypt · Cointelegraph · The Block

Rahil Jain, Co-founder, Chalk Labs. Ex-Goldman Sachs engineer. You talk to the person who builds it.

Get VisualTorch running in your business

Tell us what you want to automate. A founder replies within one working day with a plan, not a pitch deck.

Need help deploying VisualTorch?

Call Get help

Cite this page

VisualTorch MCP server. Agent Mart. https://agentmart.dev/connectors/willyfh-visualtorch (last updated 2026-10-24)