"PyTorch" matching MCP servers:

A full-featured MCP server for PyTorch documentation workflows, providing tools for search, symbol lookup, code examples, troubleshooting, and question-answering using local docs.

A minimal integration layer exposing PyTorch Lightning via a structured, machine-readable API for tools, agents, and orchestration systems.

Provides semantic search capabilities over PyTorch documentation, enabling users to find relevant documentation, APIs, code examples, and error messages through Claude Code integration.

Provides access to PyTorch CI/CD analytics data including workflows, jobs, test runs, and log analysis through an MCP interface.

Enables comparing two recorded PyTorch Dynamo runs and inspecting compiler evidence behind differences via CLI, MCP tools, and a VS Code extension.

Renders PyTorch neural network architecture diagrams using VisualTorch, supporting multiple styles and customizable options.

Gives Claude Code, Cursor and other agents structural awareness of a PyTorch model: layers, params, FLOPs, blast radius, the design linter, a full readiness/cost/deployment verdict, and a ranker for which of k candidate designs to train. Reads a .py, a .neurarch.json, 81 bundled reference architectures, or a Hugging Face repo. Offline, no API key.

Enables AI assistants to estimate monocular depth maps from local or remote images and frame-by-frame video using bundled ONNX Depth Anything V2 models, without requiring PyTorch. Also exposes tools for listing and pre-downloading checkpoints and checking the runtime backend, with automatic GPU/CPU selection.

MCP server for analyzing Ascend PyTorch Profiler performance data. Enables users to identify performance bottlenecks, analyze operator time, view communication overhead, and query trace data via natural language.

Enables local analysis of scientific papers including PDF parsing, mathematical formula extraction with AST generation, PyTorch code generation from methodology, and automated Markdown report generation with visualizations.

A RAG MCP server that enables retrieval-augmented question answering over PyTorch documentation, with hybrid search (FAISS+Chroma, BM25) and source-cited responses from DeepSeek.