"Evaluating an Expo Go App and Associated React Native Code in an Android Emulator" matching MCP servers:

Publishes a spending-summary tool alongside an interactive HTML view, letting people click a category in the answer to fetch the individual expense records behind that total. Keeps calculations and their supporting evidence together in a single inspectable flow.

Enables coding agents to control a locally connected Android phone or emulator over ADB through MCP tools for device setup, UI inspection, taps, swipes, Unicode text input, app launching, and bounded batch actions, plus a live screen sidebar with clipboard capture.

This MCP server enables MCP Apps-compatible hosts to render an interactive React-based UI and invoke a sample tool over streamable HTTP or stdio transports.

An MCP server that provides live status updates for the Eco via Sirens game server, displaying meteor countdowns, player statistics, and world information directly within Claude Desktop. It also serves as a minimal reference implementation for building MCP Apps in Python without complex tooling.

MCP server delivering interactive MCP Apps UI for Megamarket shopping, enabling search, product details, cart, and checkout through native interfaces within the chat.

MCP server demo by Banco D that shows a loan application interactive widget across six steps, demonstrating three levels of agent visibility (full, result-only, and hidden) per MCP Apps (SEP-1865). It enables users to simulate a loan request with plan selection, PIN authorization, and disbursement while controlling what the agent sees.

Provides a persistent Docker computer with terminal, file editing, and optional desktop GUI control through a Three.js interface.

Enables AI agents and MCP clients to control an Android phone or emulator through ADB, including reading the screen, finding and tapping controls, typing, scrolling, and verifying results, with a live view and optional UI-decision assistance.

Provides an interactive user interface for asking questions with support for text inputs, single/multi-select options, and confirmation dialogs. It allows LLMs to gather structured input or feedback from users through a set of predefined input types.

Provides weather data from Open-Meteo with location search, current conditions, and forecasts, and can render an interactive dashboard directly in MCP hosts.

A parametric CAD workspace as an MCP server, enabling agents to create, edit, and manipulate 3D models through tools, with a live studio UI and STL/OBJ import/export.

An interactive digital audio workstation as an MCP server, enabling music production with a channel rack, piano roll, mixer, effects, automation, microphone recording, and offline WAV rendering.

Enables users to create, validate, view, and export system stock-and-flow maps from a versioned JSON model through MCP-capable hosts over local stdio or hosted Streamable HTTP. Supports causal-loop and nested-level mapping while keeping submitted model content with the caller and requiring no LLM provider key.

A demo MCP server that returns an interactive dashboard (bar chart with dataset selector) as an MCP App via the official MCP Apps extension (SEP-1865).

An MCP server that enables human-in-the-loop elicitation, letting AI agents ask users questions via tools like elicit_confirm and elicit_form, with diagnostics to verify host elicitation support.

An MCP server that lets LLM agents autonomously play retro games by driving a real OpalEmu emulator in a Playwright-controlled browser, exposing tools for loading ROMs, controlling buttons, and capturing screenshots.

An MCP server that lets Claude or ChatGPT read, create, and edit mind maps stored in a GitHub repository, with support for local and HTTP transport.

An interactive flashcard MCP App for Claude Desktop. Claude generates flashcards from your request or the conversation and renders them as an inline, gradeable flip-card review with spaced repetition.

Enables Claude to control the AI Coach desktop pet, making the mascot react to the conversation, accept care, show messages, act out activities, preview local files, and manage user memos.

Provides an inline UI in Claude Desktop to view, add, remove, and update MCP server entries in claude_desktop_config.json, with automatic backup and app restart.

Lets your AI app work inside Adobe After Effects and prove what it did: an exact change report for every edit, pixel-proven restructures, delivery checks against your own spec, template stress tests and verified farm renders.

Runs entirely locally to provide calm, animated breathing sessions that open in a browser or as an artifact, with tools for matched or custom sessions, pattern listings, and a breathing-break prompt, while collecting no data.

Deterministic, LLM-first control of Word documents (.docx). An agent reads the outline, finds text by phrase, and applies edits as tracked changes and comments in one atomic batch, with a safety layer that refuses edits based on a stale read and rolls back failed batches. It works on .docx files directly, and can also drive an open document in Microsoft Word on Windows or in LibreOffice Writer.

Enables an AI assistant to search a Hong Kong online mall for a whole shopping list, compare prices and unit prices, show product cards with photos, read order history, and set quantities in the user's real basket. It never places, pays for or changes an order, so checkout stays with the user.

An MCP server for Action1, a cloud-native RMM platform, enabling remote monitoring, patch management, and endpoint management through Action1's API.

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

Enables AI coding agents to vet an npm release against the package's own history — publisher, provenance, install scripts, new dependencies, code changes — before installing or upgrading it. Returns an ALLOW / REVIEW / BLOCK verdict with supporting evidence, what other checks say, and the safe version to install instead.

Enables users to set up and run an affiliate program from any MCP client in plain language, including planning commissions, creating campaigns, adding tracking, inviting affiliates, approving sales, and viewing payouts. It relays requests to a hosted backend using the user's sign-in or API key, with plan limits and audit logging applied.

Enables an assistant to find and view photos in one Google Photos library using Google Photos' own search and image views, with no write access.

An MCP server that lets AI models run code in 31 languages, evaluate symbolic math and logic problems, and measure complexity—exposed as 48 tools for execution, session management, translation, optimization, and more.