"Steam Deck" matching MCP servers:

Enables AI to generate fully authored Elgato Stream Deck profiles with buttons, icons, colors, dials, and shell scripts from natural language prompts.

Hand off work to agents and get back only the decisions that need a person: one ranked deck of approvals with risk levels, budgets and approval before risky steps, behind an MCP gateway with Code Mode. Open source (AGPL-3.0), runs locally or on your own Cloudflare account.

A Unity Editor MCP server that gives Claude Code full control over Unity projects through 268 tools, 7 resources, and specialized AI agents. It enables AI-assisted game development by allowing Claude to see, create, modify, and inspect everything in Unity including scenes, GameObjects, scripts, and builds.

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.

Enables users to read compact game state, execute legal actions with freshness checks, and inspect action schemas and wiki details for the Steam version of Balatro through MCP tools.

MCP server that adapts, activates, and shares local Agent Skills for runtimes like OpenAI Agents SDK and Claude Code, enabling dynamic discovery and shareable HTML/image artifacts.

An event-driven MCP server that enables agents to share context streams, publish and subscribe to events, manage tasks, and follow protocols, keeping a fleet of agents mutually context-aware in real time.

Enables AI agents to control a simulated Pollen Robotics Microduck through MCP tools for movement, tricks, pushing, camera views, and state inspection.

Connects AI assistants to the ADAS platform, enabling them to build, validate, and deploy multi-agent systems through natural language commands without manual configuration.

Provides multi-agent equity research for US markets with provenance-backed financial data from SEC EDGAR, technicals, macro, and Alpaca paper trading, enforcing risk limits and journaling theses.

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 orchestrating a reusable team of expert agents (PM, architecture, development, QA, security) to analyze a project's files and produce consolidated recommendations. It exposes tools to list experts, ask a single expert, or run the full team from MCP clients.

Turns Claude Code into a self-driving AI company with autonomous CEO, agent teams, and self-improvement capabilities.

Enables users to leverage a team of specialized AI agent personas like Business Analysts and Product Managers through a unified interface across multiple LLM providers. It streamlines agile development workflows by providing tools for model discovery, unified prompt delivery, and role-specific decision making.

An MCP server that acts as a bridge to query multiple OpenAI-compatible LLMs with MCP tool access. Just like rubber duck debugging, explain your problems to various AI "ducks" who can actually research and get different perspectives!

Enables collaboration between multiple AI models (GPT, Claude, Gemini) to work together on complex tasks, with intelligent task distribution and role-based expert assignment for code development, review, and optimization.

Enables delegating coding tasks to the Pi CLI through MCP with named sessions, synchronous or asynchronous execution, and a read-only transcript window on Windows.

A Model Context Protocol server that allows AI applications to interact with Crawlab's functionality through natural language, enabling spider management, task execution, and file operations.

Enables autonomous hierarchical multi-agent orchestration for MCP, with persistent SQLite state, real-time web monitoring, and support for mixing multiple CLI and direct API execution providers.

Enables a Lead agent to spawn persistent teammate sub-sessions that share a working directory, coordinate work through a shared task board with CAS-guarded task actions, and exchange messages across members. Ships a live MCP Apps panel for real-time team status alongside tools for listing agents, waiting on progress, and interrupting teammates.

Enables AI clients to see and control a Windows desktop through screenshots, built-in OCR, mouse and keyboard input, and accessibility trees read via UI Automation, MSAA and Chrome DevTools Protocol. It also manages windows, virtual desktops and element-level actions such as invoking controls or setting values, running on Node.js with the PowerShell that ships with Windows.

MCP serverr for Lastest to manage your tests, AI create them, run them, and speed up AI-development.

Connects MCP-capable assistants to support tickets and Agent Tasks through OAuth, exposing read tools for tickets, bots, task runs, and report templates. It also provides scoped write actions such as ticket replies, status and tag updates, draft approvals, task creation, and run decisions.

A Model Context Protocol (MCP) server that turns multiple AI coding agents into a coordinated team that chats, debates, remembers, audits security, and works in parallel on the same project.

This MCP server provides research-backed prompt optimization tools and professional domain templates designed to improve AI performance through strategies like Tree of Thoughts and Medprompt. It enables users to analyze, auto-optimize, and refine prompts using advanced reasoning patterns and safety-critical alignment techniques.

Enables Claude Code to orchestrate a team of independent Claude Code sessions within iTerm2 for parallel task execution and isolated git worktree management. It provides tools to spawn, monitor, and message worker sessions while maintaining full visibility and control over their terminal windows.

Enables Claude Code to operate as an autonomous multi-agent company through MCP tools for task orchestration, agent memory, meetings, tool governance, and persistent workflow observability.

A reusable AI software development team built on MCP. 13 specialized agents (Project Manager, Backend, Frontend, QA, Security, DevOps, UX, and more) collaborate via shared SQLite state. Exposes 44 MCP tools across 12 domains. All discussions and decisions are stored in the database so agents get back up to speed immediately when re-loaded.

Enables autonomous AI agents to invoke metered upstream tool APIs through a policy firewall that enforces per-key cent-level spending caps and strict tool allowlists, blocking unauthorized or over-budget calls pre-flight. Every transaction is settled atomically and returned with an HMAC-SHA256 signed audit receipt, with instant key rotation and spread accounting built in.

Enables owner-approved agent transfers: an owner sets limits, reviews requests, and approves exact contents while agents prepare and execute approved plans, including local simulation and unsigned Sepolia preview.