MCP server for reading, filtering, and analyzing NVIDIA Nsight Graphics captures via ngfx-replay, exposing tools for capture inspection, GPU Trace profiling, and replay analysis.
A FastMCP server providing structured SVG authoring tools for LLMs, enabling create, edit, and render SVG graphics through hierarchical primitives, gradients, paths, and reusable resources.
Enables interactive editing of scientific SVG figures in chat, allowing users to open, inspect, modify, undo/redo, and export SVGs through direct manipulation or natural language commands.
Enables annotating SVG paper figures in the browser by picking elements or drawing regions, and feeds those annotations back to Claude via MCP so it can edit the underlying SVG or generation scripts, with automatic page refresh on changes.
A custom MCP tool that integrates Perplexity AI's API with Claude Desktop, allowing Claude to perform web-based research and provide answers with citations.
Enables creating and iterating on animated SVG diagrams from text input, photos of sketches, and YAML specifications, with support for shapes, connections, SMIL animations, and file output.
Enables literature search, local Zotero reading, PDF parsing, citation tools, materials data, and scientific image generation for coding agents through a local Python MCP server.
Enables high-quality conversion of SVG files to PNG, ICO, and JPG formats with optimized Chinese character rendering. Supports single file, batch, and string-based conversions using multiple rendering engines including Cairo, SVGLib, and PIL.
MCP server that routes natural language requests to structured tool calls using a LoRA-tuned small language model, with built-in validation, retry, and fallback recovery.
Enables AI agents to control a Playwright-driven browser through natural-language instructions, including page interaction and live browser task execution.