Tools

Renders a component anatomy annotation in Figma: numbered markers on an instance with an attribute table, plus a section per sub-component listing its internal elements, hidden ones included. Part of uSpec; needs the .md spec from create-component-md, a Figma MCP and a configured template.

Renders a screen reader spec for a component directly in Figma: focus order plus per-state VoiceOver (iOS), TalkBack (Android) and ARIA (Web) property tables and announcements. Part of uSpec; reads the component .md spec from create-component-md and needs a Figma MCP and a configured template key.

Official ComfyUI plugin for Claude Code: installs the hosted Comfy Cloud MCP plus slash commands to generate or edit images, video, audio and 3D models, remove backgrounds and upscale. Needs a Comfy account; model search is free, generation needs a Comfy Cloud subscription after 5 free runs.

Official ComfyUI plugin that connects the hosted Comfy Cloud MCP: slash commands to generate images, video, audio and 3D, remove backgrounds, upscale, and search models, nodes and workflow templates. Needs a Comfy account and sign-in via /mcp; 5 free runs, then a paid plan.

Searches Unsplash's free high-res photos by keyword, color and orientation to find images for posters, articles, slides and designs. Needs a free Access Key from the Unsplash developer portal; clone the repo and run the Python server with uv.

MinerU's official MCP: parses PDF, Word, PowerPoint and images into Markdown via the mineru.net cloud API, keeping tables and formulas. The keyless Flash mode works out of the box; add a token for higher quotas and more formats.

Comet's official Opik MCP: query traces and spans of LLM apps in chat, log scores and comments, and manage datasets, experiments and prompt versions. Works with Opik Cloud (API key or browser sign-in) and self-hosted open-source Opik.

Designs or restyles web UIs in a neo-industrial, editorial-brutalist style: sets a mode, one dominant gesture, a grid and a single accent color, builds type hierarchy and layout from macro to micro, and reviews the rendered page at desktop and phone widths.

Compiles AI-written OpenSCAD code or dimension parameters into editable SCAD and STL models, renders previews from four angles and can export 3MF. Good for parametric parts and 3D printing. Needs OpenSCAD and Python 3.11+ locally; clone the repo and run with uv. No API key.

Wraps Shapely, GeoPandas, PyProj, Rasterio, PySAL and other GIS libraries so agents can run geometry and overlay analysis, reproject coordinates, process rasters (e.g. NDVI), do spatial statistics and make maps, and fetch boundaries, land cover and satellite imagery. Needs Python 3.10+ and uv.

MongoDB's official plugin: runs the MongoDB MCP locally via npx and adds skills for query generation, index tuning, schema design, and full-text and vector search. Connects to self-hosted or Atlas databases with a connection string.

MongoDB's official skill library covering document model design, driver connection setup, query optimization, natural-language query generation, Atlas full-text and vector search, and stream processing. Works alongside the MongoDB MCP Server.

Miro's official plugin with the Miro remote MCP and three skills: draw codebase explanations on a board, run visual code reviews on the board, and turn board docs, diagrams and prototypes into development specs. Needs OAuth with a Miro account.

Applies a Swiss International Style design system with Tailwind CSS: a 12-column grid on an 8px base, IBM Plex Sans with light headings, a stone palette, hierarchy through opacity rather than hue, a single accent color, body text capped at 60ch, mobile-first layouts and dark mode.

Canva's official plugin: through the Canva MCP server, edit designs, revise them from review feedback, generate in bulk from brand templates, resize designs for each social platform, and check consistency against your brand kit. Needs a Canva account; bulk generation needs an Enterprise plan.

Microsoft Translator's translation quality tool: GPT scores each sentence using MQM error categories or a direct score; --list_mqm_errors shows error types and severity. Needs line-aligned source and target files, Python and an OpenAI or Azure OpenAI key (paid); a translator should still review.

Connects AI to Autodesk Fusion 360 with 90+ tools for sketches, extrude, revolve and loft, chamfers and shells, booleans, sheet metal and patterns, to automate part modeling. Needs Fusion 360 with the repo's add-in copied into its AddIns folder and started, plus uv. Beta.

Styles elevated surfaces such as cards, dialogs, popovers and toasts with smooth-shadow-ring utilities instead of pairing a border or ring with a shadow, avoiding the double-edge look. Covers ring and shadow tinting, dark mode and overrides. Requires the shadow-plugin Tailwind plugin.

Webflow's official MCP: manage your site's pages, CMS content and blog posts by chat, and with the MCP Bridge App in the Designer, edit page elements and styles directly. Needs a Webflow account and Node.js 22.3+; first connection asks you to authorize sites.

Official Black Forest Labs skills: teach agents to write strong FLUX image prompts (typography, exact color values, multi-reference editing) and call the BFL API to generate images, FLUX 3 short videos with sound, and product ads. Prompting needs no API; generation needs a BFL API key.

Connects any FHIR-compliant EHR server (e.g. the Epic sandbox or HAPI) to agents to search, read, create and update patient clinical data in plain language, with SMART on FHIR auth. By WSO2. Needs a FHIR server URL, access token and uv; clinicians must review results.

Skill for naming products, brands, companies and open-source projects: writes a naming brief, explores metaphors, generates candidates while filtering out generic AI-style names, scores them on a rubric, then checks domain, social handle and package name availability. Good for early-stage startups.

When the user describes a concept in their own words that matches an established term of art, the agent appends that single term after its answer, linked to a Google Images search, so the user learns the proper name and can see examples.

Turns one idea into a sparse, wordless white-chalk illustration on an even green board. Picks one of six composition families, generates an image, checks it against a gated QA list and repairs it up to twice. Needs image generation and inspection; otherwise returns the prompt and recipe.