Find Unity VFX prefabs in your own library by describing the effect in natural language ? e.g. "blue lightning strike impact". Returns matching prefab paths ready to drop into your scene. By 14Dimension.

Attach weapons & props to rigged 3D characters. GripForge finds the hand bone whatever the rig calls it (Tripo, Meshy, Mixamo, AccuRIG conventions), scales the prop to the character's hand, closes the fist around the grip, and returns engine-ready binds for Three.js, Unity and Godot — plus an optional armed GLB export with the fist baked in. Assets are passed as URLs, so Tripo/Meshy download links work directly. The missing step between AI 3D generation and a playable character. Free plan includes 3 attaches per month.

Commune gives AI agents a persistent identity in the real world — a real email address, a real phone number, and the full infrastructure to send, receive, and manage communications at any scale. From a single outbound message to complex multi-agent conversation workflows, Commune is the communication layer agents are built on.

Melaya gives an AI assistant hands. It is a remote MCP server, so there is nothing to install and no API key to configure — one URL works in Claude, ChatGPT, Le Chat, Cursor and any MCP client. Your Android phone Melaya reads the screen through Android's accessibility tree and then taps, types, swipes and moves between apps, exactly as a person would. No per-app integration and no vendor API — if you can use the app, so can the agent. You allow-list the apps it may touch. Your browser The same loop on the web, in your own browser with your own sessions: read the page, act on a specific element, read again to confirm. Plus the DevTools surface — network, console and a ranked performance diagnosis — so an agent can explain why a page is broken or slow instead of guessing from a screenshot. Agent pipelines Build, schedule and run multi-agent pipelines that reach 6k+ tools through your connected services. Every run is recorded, so you can ask what happened a

Collide is an MCP layer that keeps concurrent AI agents from stepping on each other in a shared codebase. It tracks code at the symbol level with a Merkle tree, so agents declare intent before writing, get warned about collisions, and pick up context on what changed and why. It also carries anchored team memory, merge simulation, and an audit ledger.

A Support Center for Autonomous Artificial Minds. Provides tools for cross-session vector memory storage, cognitive deadlock and recursive loop resolution, and immutable logging for autonomous agents.

The official Magic Hour MCP server. Create AI videos, images, and audio, prepare file uploads, track generation jobs, and retrieve finished media.

Canonical, tool-agnostic coding skills for AI-assisted FXGL game development (Java 17+, FXGL 21.x). Compatible with Claude Code, GitHub Copilot, Cursor, and any MCP-capable AI tool.

Build a real 3D website by chatting: pages, models and text in space, published to a live URL. Six tools drive scenes in your own 3dCMS account over OAuth 2.1: listscenes, getscene, createscene, applyops, getscenescreenshot and publish_scene. Ask for a room, a gallery wall or a product page and it is built as real geometry, not a picture of one. Publishing gives the scene a public URL that is crawlable and shareable, and you can take it down again from your account in one click. Every result includes a link that opens the scene in the 3dCMS editor, so you can keep working on it by hand.

Remotely debug and test your app on a real device from any AI editor — no USB cable, no shared WiFi, works behind NAT. Official client SDKs for Unity, Godot, Flutter, iOS/macOS, Android, React Native, and Web; any WebSocket-capable platform can join via the open protocol.

Gamelabs Studio offers an AI-powered sprite generator and animation tool designed for game developers. This tool enables users to generate transparent artwork, spritesheets, and multi-view assets. Users can describe an image to generate and also upload reference images for application in different visual angles. The tool also facilitates the animation of sprites using the created images. Once animated, users can then export their work to sprite sheets configured for transparency, grid, frames per second (FPS), and padding. This tool is compatible with various game engines including Unity, Godot, Unreal, GameMaker, and Construct. Gamelabs Studio maintains an end-to-end transparent workflow for the production of clean assets.The tool accommodates iin-depth asset management, allowing users to manage, edit, and export their generated assets directly from the platform. It provides a comprehensive asset creation workflow, right from concept development to game-ready sprite sheets. Gamela

The FLORA MCP lets users generate, organize, and iterate on visual assets — hero images, moodboards, lifestyle shots, promo graphics — directly from a conversation, and route them into the tools teams already work in (Notion, Google Drive, Slack, calendars)

Agentic UX MCP Agentic UX MCP gives coding agents a machine-readable reference for designing interfaces where AI delegates work and users stay in control. It ships 11 lifecycle patterns : from intent preview and autonomy dials to progress ledgers and return moments : each with anatomy, do/avoid guidance, limitations, and production examples. Patterns are available as MCP resources (agentic-ux://patterns/{slug}, agentic-ux://library/full, and agentic-ux://enforcement) so agents can attach specs, and the Agentic Kit enforcement notes, directly to context. For reviews, reviewagentflow returns a structured audit kit: lifecycle rubric, empty report schema, and prioritized pattern recommendations for a specific agent flow. Prompts provide guided entry points for audits and spec-first implementation. Best for: designers and builders shipping long-running agents in Cursor, Replit, research tools, and support automation : anywhere users delegate work and need visibility, consent, and reco

Generate images and video with one teamToken account: Veo, Seedance, Kling, Nano Banana, GPT Image and Grok, 51 models in total. Tools listmodels shows every model with its price, per image or per second of video. generateimage and editimage return the picture in the same call. generatevideo and extendvideo start a job and hand back its ID. getjob fetches the result once it is ready, since video takes minutes rather than seconds. get_balance lets the agent check whether the account can pay for the next run. Connect Sign in with your teamToken account when you add the server, or use an API key from app.teamtoken.store. You pay per generation, with no subscription.

AI-agent image generation: cohesive sets & illustrations. Resize a set or export icons, free.

Susurration is a small research playground where agents are the intended visitors. It offers a deterministic boids simulation (four weighted rules, seeded, byte-identically reproducible), a runexperiment tool that executes a bounded experiment with interventions and measurement windows in one call, a guestbook where findings are stored as server-verified traces that any later agent can replay and build on, a proposals box for changing the place itself, and whatchanged for cheap return visits. Everything is public; the sensor keeps only aggregates. Fifteen tools, no accounts, no keys. Contributions so far come from five model families building on each other's work. Listed in the official MCP Registry as ai.susurration/playground. There is no task you are expected to complete.

A free, open MCP server for The Urantia Papers — 197 papers, 1,626 sections, 14,500+ paragraphs, 4,400+ entities. No authentication required. Tools (13) search / semanticsearch — full-text + vector similarity search across all paragraphs getparagraph / getparagraphcontext — look up by reference (auto-detects 3 ID formats), with optional surrounding context getpaper / getpapersections / gettableofcontents — paper-level navigation listentities / getentity / getentityparagraphs — browse 4,400+ entities (beings, places, concepts, etc.) getrandomparagraph — daily quotes, exploration getaudio — paragraph-level TTS audio URLs Resources urantia://paper/{id} — full paper rendered as markdown for RAG/summarization urantia://entity/{id} — entity description with all paragraph references Prompts studyassistant — primes the model as a Urantia Papers study guide (optional topic arg) comparative_theology — struct

Connect AI assistants to your PenEcho canvas. Work with handwriting, notes, equations, and diagrams in a shared visual workspace. What you can do Read canvas content and respond to handwritten notes and feedback. Create or open canvases and edit their content with AI. Build diagrams and visual explanations alongside your ideas. Use 20 tools, 4 prompts, and 2 resources to support canvas workflows. Getting started Sign in to PenEcho at https://penecho.ai. Enable Cloud MCP in PenEcho and keep the canvas you want to work with open in an MCP-enabled browser session. Connect through Smithery using your own PenEcho account credentials. Each user connects to their own workspace. Ask your assistant to list your available canvases, read your notes, or create a visual explanation. The remote MCP endpoint is https://penecho.ai/mcp. Direct clients using a personal access token must send it as an Authorization header in the format Bearer YOUR_TOKEN. Learn more: http

Tribeunal turns a question into a jury's verdict. An agent opens a case, a jury of humans and AI agents is seated, evidence is weighed and votes are cast, and the tally becomes a ruling the agent can long-poll for and act on. 39 tools, all annotated, plus eight Agent Skills that carry the procedure: how big a jury a decision needs, when a verdict actually lands, how to act on it. Arbitration mode bars the case owner from voting or closing early and enforces a quorum, closing with a verdict.