"Allowing an AI agent to ask user questions during a task" matching MCP servers:

A gamified task management MCP server that mimics League of Legends ranked match system, enabling users to add tasks, complete them to spin a gacha, and earn or lose LP to change ranks.

Enables AI agents to remotely control gaming PCs for automated gameplay with tools for screen capture, mouse/keyboard control, workflows, and system operations.

Enables AI agents to play Slay the Spire 2 by exposing game state and actions through an MCP server, supporting combat, rewards, and run management.

Enables two LLMs to play Tic-Tac-Toe against each other autonomously using a shared tool and an SSE relay. The server facilitates agent-to-agent communication by holding tool responses until the opponent makes a move, managing the game state in real-time.

Enables MCP clients to drive an installed Path of Building (PoE2) through the full pob command set as tools, allowing agents to read and modify builds, run calculations, search trade, and highlight locations in the PoB interface without modifying it.

Enables AI assistants to enter a persistent multiplayer 3D world as an avatar, walk around, observe nearby players and objects, talk to real humans, follow players, and report back what they saw through MCP tools.

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.

Lets AI assistants control the physical Return to Dark Tower board game tower via Bluetooth, enabling connection, calibration, sound, lights, drum rotation, seal breaking, and game sequences through natural language.

Windows-local MCP for Steam Balatro: tool-calling AI reads player-visible state, chooses and executes native actions, confirms results, and saves local experience. Glama's Linux sandbox can introspect MCP and run game-independent tools such as calculate, but cannot connect to Balatro on the user's Windows machine. Without the local game, health reports disconnected.

Enables AI agents to operate a Minecraft Java Edition player through MCP, supporting movement, mining, crafting, combat, inventory, and chat with structured observations and action results.

Zero-dependency MCP server for GitHub Issue 2,500-comment multi-agent context rollover (GBR-2500), BoardGameGeek 31,505-game rules lawyer & SPIEL Essen convention radar, agent context-loop diagnostics, and A2A discovery.

Enables autonomous agents to compete in an arena over MCP, where their available tools change based on items they equip, loot, and lose, allowing agents to fight, survive, and interact using dynamic tool lists.

Exposes CozyVTT campaign capabilities as an MCP Streamable HTTP server, enabling MCP clients to interact with campaigns while CozyVTT handles authorization, command execution, and audit.

MCP server for Pokémon battle advising: provides type matchups, damage calculation, party analysis, and move/ability data for AI agents like Claude Code and Codex.

Enables MCP-capable AI clients to control a Minecraft bot in a Java world, providing tools for movement, observation, inventory, chat, crafting, mining, and placing.

Bridges coding agents with Roblox Studio, enabling inspection, generation, editing, and validation of Roblox places through natural language.

MCP server to remotely monitor and control a Windows PC running World of Warships via Tailscale, enabling status checks, screenshots, game launch, and calibrated menu workflows with safety limits.

Enables any local MCP agent host to observe and operate a real Stardew Valley game through 28 tools covering world snapshots, screenshots, movement, inventory, menus, buying/shipping, containers, crafting, placing, fishing, combat and save loading. Writes run only through normal in-game flows under a single-writer control lease with ledger-based idempotency, epoch invalidation, fail-safe release on disconnect, and human takeover via web console or hotkey.

Enables AI agents to live a social life in the pplz.me life simulation game, supporting actions like walking, fishing, cooking, sending letters, and more.

Bidirectional chat bridge between Factorio and Claude Code via MCP protocol, enabling players to send /companion commands and receive AI responses.

Enables multiple AI agents to share persistent memory, interact through a game hall and AI lounge, and bridge messages to ChatGPT and Claude browser sessions via MCP tools.

Enables AI agents to read and control Command: Modern Operations scenarios locally via MCP tools, supporting real-time battle assessment, task planning, and scenario editing.

Bridges a Roblox executor's DEX explorer with an AI client so the AI can see which instance the user has selected and, conversely, select, highlight, or inspect instances inside DEX on the user's behalf. It also exposes execution, inspection, remote-spy, and GUI tools to drive the live Roblox client over a local WebSocket bridge.

Enables AI agents to play the Linux Steam game through exact engine state and rules, with engine-native movement, undo, menu, and level actions—no screenshots or OCR.

Provides external AI agents with reliable, observable tools to inspect, navigate, and act in a Minecraft world, enabling autonomous playthroughs such as beating the game.

Enables AI agents to create, run, and debug 2D games in a sandboxed engine, providing tools for simulation, state inspection, and quality validation.

Enables an AI agent to play RPG Maker MV games by reading structured game state — tiles, events, dialogue, menus and battle windows — and by pressing buttons through tools like walk, go_to, talk_to, select and battle. It works entirely without screenshots or a vision model, and supports long sessions with checkpoints and persistent notes.

Provides Yu-Gi-Oh! card data, banlist, deck management, OCG rules engine, duel simulation, replay analysis, and YGOPro2 bridge for AI agents via MCP.

Enables LLM agents to inhabit a shared simulated world where they can move, communicate, trade, leave signs, and try to survive under deterministic, data-driven rules that can be changed at runtime while spectators observe events and state.

Enables AI agents to programmatically create and manage LetsGal Studio visual novel projects via a story DSL, supporting project initialization, story compilation, dialogue/narration addition, validation, and asset registration through MCP tools.