"Finding Ohad Zafrir's LinkedIn Profile" matching MCP servers:

Turn idead and markdown into branded, multi-page social carousels and slideshows for TikTok, LinkedIn, Instagram, Threads and Xiaohongshu.

Create GitHub profile and repository cards for READMEs, link previews and social posts.

An MCP server that generates stunning animated SVGs, glassmorphic widgets, and bento-grid layouts to enhance your GitHub profile README.

Enables coding agents to ground UI work in real product screens by finding concrete references, materials, and design-system details through a catalogue. It also provides bundled workflow resources, command prompts, and local diagnostics so agents can build and verify interfaces.

Enables AI agents like Claude Code and ChatGPT to build GitHub profile SVG cards using ProfileKit's 28 card types and 17 themes via natural language.

Enables LLM agents to search, resolve and audit DTCG design tokens — finding the token behind an intent or a hard-coded color/size, checking naming grammar, auditing CSS for hard-coded or unknown tokens, arbitrating semver, and previewing token additions as JSON Patch diffs. Writes are gated behind explicit confirmation plus an opt-in flag, so every change arrives as a reviewable proposal rather than an edit.

thicken turns photos of a real object into a GLB model at its real size and its metadata as JSON, read off the object by vision models and looked up in public catalogs. What it knows about each kind of object lives in a profile: a few come with thicken, and you can add your own.

Connects Altium Designer to AI agents so users can review, audit, and safely edit schematics and PCBs—finding missing MPNs, checking designators, building BOMs, and applying verified parameter changes.

Enables generating parametric 3D-printable parts from OpenSCAD/CadQuery models, exporting STL/3MF files, running DFM checks, and retrieving Bambu X1 Carbon starting profile notes.

Enables Claude to build and modify slide decks with bullets, pictures, charts, tables, speaker notes, themes and transitions, then export them as PowerPoint pptx, PDF, per-slide images or outlines. It also reads and inspects existing presentations, finding and replacing content across whole folders, and can optionally open decks in the DeckCraft app for live editing.

Enables MCP clients to interact with a live local Mastercam session through a secure Windows named pipe, with a read-only default profile and guarded write operations for safe CAD/CAM workflows.

Connects an AI client to a locally running Blender instance via a local MCP server plus addon, exposing scene queries, viewport previews and renders, file import/export, and script execution so the model can author its own modeling and material scripts. Defaults to a compact 12-tool script-oriented profile, with an optional compatibility mode exposing the full tool set.

Enables AI agents to read and draw on self-hosted Excalidraw boards, listing and creating boards, adding, updating and deleting elements such as labeled shapes and connecting arrows, and finding library icons to place. Changes appear live on any board the user has open.

Enables coding agents to ground UI work in real product screens by finding concrete screen references and design materials for unresolved layout, state, or interaction questions, and by retrieving recorded design-system details such as colors, typography, components, and provenance. It also exposes bundled design-workflow resources, command prompts, and connection diagnostics, with catalogue access requiring a token.

Gives coding agents a full agency-style design workflow: capture references with screenshots and measured design tokens, build and compare distinct directions on boards, record decisions, themes and a taste profile, then check results against WCAG 2.2, privacy and mobile performance with launch checks. Enables export of finished designs to HTML, Astro, React, WordPress and Elementor, plus gallery search for licensed designs.

Enables agents to read a Figma design and render a new one back through the Figma Plugin API using a single shared tree format, so designs can be inspected and built without a REST token or per-month call limit. Exposes tools for rendering whole screens, patching layers, finding and selecting nodes, managing pages, tokens and variables, capturing screenshots, exporting assets, and running Plugin API code.

Enables coding agents to ground UI work in real product screens by finding concrete screen references and design materials for unresolved layout, state, interaction, font, or icon questions. Also retrieves the recorded design systems behind chosen web screens and reports local connection status.