"Paradox Interactive" matching MCP servers:

Enables AI agents to create, render, and validate 3D scenes, 2D art, and games in HTML canvas using Three.js, WebGL, or Canvas 2D, with multi-angle screenshots, structured validation reports, and interactive playtesting.

Enables AI agents to generate, execute, and compile interactive Manim slide presentations through MCP tools.

Turns any idea, blog post, or article into hand-drawn Tinku illustrations that explain key concepts, with an interactive viewer in the chat.

Enables extraction of recipes from PDFs or JPG files and conversion into structured HTML, with interactive region selection and OCR via a web GUI.

Enables agents to extract multi-page financial tables from complex PDFs, rasterize vector pages into crisp 300 DPI images for vision LLMs, flatten interactive AcroForm/XFA forms, and dewarp skewed OCR bounding boxes from photographed or scanned paper documents. Tool invocations are gated by USDC micropayments settled on Base L2 via the x402 protocol.

Enables turning a photo or character description plus a story idea into an interactive, mobile-friendly landscape children's picture book with Lift-the-Flap pages, built as a self-contained HTML file and served locally over Wi-Fi.

A Model Context Protocol (MCP) server for the @visactor/vchart that enables AI assistants to generate interactive charts and visualizations.

Combines screen vision, RuneLite HTTP API, click coordinates, OSRS Wiki lookups, and Grand Exchange prices to give AI agents eyes and knowledge for playing Old School RuneScape. Enables game state analysis, skill tracking, item/NPC lookup, and interactive automation.

Enables creating immersive, interactive websites from scratch and transforming existing sites into immersive experiences, with scroll-driven frame scrubbing, business modules, a video/frame pipeline, and automatic headless verification. Works across any MCP client such as Claude Code, Cursor, VS Code, Gemini CLI, and Codex.

Enables MCP clients such as Codex and Claude to plan natural-language or timed actions, generate and revise skeletal motion locally through a Kimodo runtime, and review results with diagnostics, candidate comparison, and interactive 3D previews. Provides checked handoffs of verified exports into Blender and Unreal Engine.

Enables MCP-compatible clients to render, inspect, and diagnose OpenMoonRay scenes through a local MoonRay runtime, with support for interactive viewing, scene validation, and render comparisons.

Provides comprehensive functionality including weather data, system utilities, Azure cloud management, and AI-powered image generation and editing. Features interactive parameter selection through MCP elicitation for enhanced user experience.

Enables AI assistants to build, edit, check and publish live 3D, AR and game scenes, including object placement, AR anchoring, interactive cards, events, scripts, and shareable links that open on phones.

Enables 3D visualization capabilities through PyVista integration, allowing users to generate and export interactive 3D shape grids as HTML files. It provides tools for creating visual representations of geometric objects like cylinders, spheres, and arrows.

Enables interactive sprite operations, inspection, palettes, text, style presets, dream-animation automation, QA gates, and export backends such as PNG sheets, WASM-4, TIC-80, and VoidSprite file interop, with all paths project-root bounded.

Local-first MCP image generation server supporting OpenAI and Google Gemini models for generating and editing images, with an embedded interactive studio.

Enables AI coding agents to perform end-to-end medical image analysis locally, from inspecting CT/MRI/X-ray studies and running containerized segmentation models like MedSAM2, TotalSegmentator, and HD-BET to refining masks, measuring volumes, and writing reports. It pairs preset or custom guideline protocols with a code-customizable viewer that renders images back to agents as annotated PNGs and to humans as interactive HTML.

Opens, inspects, and renders DXF/CAD drawings for AI agents: describe_dxf returns structured facts (layers with actual drawn colors, units, bounds, text content) and render_dxf returns PNG images. On MCP Apps hosts like ChatGPT and Claude, view_dxf opens an interactive in-chat viewer with pan, zoom, and layer toggles.

Enables AI agents to load web pages in true-to-size iPhone, iPad, and Android device frames, capture screenshots, inspect interactive elements and layout diagnostics, and automate tap/type/scroll flows with network mocks, console errors, and test evidence.

Enables an AI agent to screen-record a live Expo app on a connected phone, auto-plan and direct the footage with captions, motion graphics, pop-outs and sound, then export a 1080p MP4. It also opens an interactive studio where users refine scenes by dragging, resizing, or typing prompts, and exposes all app_* control tools from expo-mcp-bridge in the same session.

Provides AI-powered medical image analysis tools for LLM agents, enabling tasks such as X-ray classification, interactive segmentation, and visual question answering. It supports multi-step diagnostic reasoning and clinical workflows through a suite of specialized medical AI models.

Enables print-on-demand sellers to design and price a product, publish it to a Fourthwall shop, generate two short UGC-style video ads, and build a Meta Advantage+ sales campaign with five automated rules from a ChatGPT conversation. It coordinates Fourthwall, Meta Ads, and fal through local MCP tools and interactive cards.

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.

A remote MCP server exposing developer utility tools that compute QR codes, JSON diffs and formatting, base64/URL encoding, hashes, JWT decoding, cron explanations, timestamp conversions, placeholder images, flowcharts, HTML/React forms, color scales and regex matches with exact results. Results can be previewed, edited and exported in an interactive workbench where the host supports MCP Apps.

Enables interactive selection of image regions from images and PDFs, with OCR support and automated export of selected regions as separate files.

MCP server for creating math animations with manim, enabling AI-driven real-time interactive creation and browser preview.

Enables Claude Desktop to capture screenshots through an interactive region selection interface, automatically saving timestamped images to a configurable directory for analysis and documentation.

Enables creating layered 3D reliefs from selected parts of a photo, producing GLB files and a self-contained HTML viewer that tilts with the pointer, with interactive approval of the segmentation before writing files.

Enables MCP clients to read the Anatomy skill's knowledge and examples, build and audit interactive isometric figures, verify them in headless Chrome, and prepare a community gallery publish. All tools return JSON with command output and exit codes passed through for diagnosability.

Enables MCP clients to geocode and reverse geocode places, render static maps with markers or routes, generate privacy-safe area maps, and get setup code for interactive maps using OpenStreetMap data.

A Model Context Protocol server that lets an LLM open web pages, list interactive elements, take screenshots, and draw annotations with color contrast selection.

Exposes 51 tools that let MCP clients open code-based videos as an interactive timeline and edit them directly: retyping on-video text, dragging numbers and colors in the drawing code, moving and muting sounds, and leaving notes on frames. Also covers image generation and exporting to MP4, WebM, GIF, PNG or a single frame with platform presets.

Enables Claude users to generate structure-preserving photoreal remodeling renders from reference images and finish descriptions, with an interactive gallery, refinement, upscaling, and a searchable render library. It also supports general image generation and optional JobTread job filing.

Generates clean, PG-13 dad jokes using AI and creates visual illustrations to accompany them on beautiful web pages. Works seamlessly with Cursor's Auto feature for interactive joke creation through natural language prompts.