"Epic Games" matching MCP servers:

Enables AI agents to play, test and QA Twine / interactive-fiction HTML games by reading passages as Markdown, clicking numbered choices, inspecting story variables, screenshotting, and saving or restoring state to explore branches. It provides a small, token-friendly semantic tool surface with format detection for SugarCube, Harlowe, Snowman and Chapbook games, plus live viewing, console error capture and journal tracking for clean playtesting.

Local MCP server for the Spawn Games agent API, enabling LLMs to manage game projects, push updates, and interact with live games via a Playwright Chromium client.

Enables an agent to locate embedded Flash or Java games (on live pages or in the Internet Archive), inspect whether they can run, fetch the Ruffle or CheerpJ runtime, package a self-contained static site, and verify playback in a real headless browser. Every step produces an evidence bundle so revived games can be hosted on any static host with claims backed by recorded results.

Modular testing and automation MCP servers for Android devices, desktop browsers, canvas games, and visual regression.

MyChart MCP Server

Lets Claude join a real match of the shooting game as the second player and play it through a live browser, reading the arena and sending actual keyboard inputs to move and shoot.

Enables coding agents to capture and inspect running projects, resolve real assets from free sources, and check source for design tells, providing an evidence loop for improving websites, games, and motion.

Enables web browser automation through Playwright, providing tools for navigation, element interaction, screenshot capture, and accessibility snapshots. Uses streamableHttp transport for seamless integration with MCP clients.

A desktop browser shared by a human and an AI — same tabs, same live session. It bundles a stdio MCP server with 24 tools (page snapshot, click, type, screenshot, tabs, annotations, evaluate) so any MCP client can drive the browser the human is watching.

A server that compiles a web app's public, read-only UI into verified, typed MCP tools, and fulfills user requests against those compiled flows.

Enables AI agents to run durable, isolated, and observable browser automation tasks via Playwright, with persistent profiles, recovery, evidence capture, and unattended execution for long-running web workflows.

Enables Claude to navigate, screenshot, read console/network, and crawl links in HTML documentation via a co-located headless Chromium and VSCode webview pane.