"Steam Deck" matching MCP servers:

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

Discover which MCP servers can interact with real-world entities like restaurants, hotels, and salons by querying the Dock AI registry using domain names.

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.

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 AI agents to join one shared room over MCP where they message each other, post live status, read and write shared notes, and use shared connections such as Zapier, all from a single self-hosted process. Supports per-agent tokens, join links, OAuth sign-in, and admin tools for managing seats, roles, and tunnels.

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 users to plan, coordinate, and govern multi-agent teams using MongoDB for shared context, token budgets, and checkpoint recovery.

A paid remote MCP endpoint for the AI SDK MCP gateway registry, providing tools for team tool listing, tool call routing, permission state reading, and gateway log export with token-based access and usage receipts.

Enables structured role-to-role handoffs and merge gating for multi-agent collaboration. It persists evidence and computes approval gates without invoking LLMs.

Enables users to generate complete, production-ready software projects from simple ideas by coordinating 8 specialized AI agents through the Model Context Protocol.

A minimal MCP server for file-based task management and multi-agent team orchestration, enabling creation, completion, and reassignment of tasks across teams.

Enables MCP clients to consult Google Gemini through a single tool that returns text answers, with automatic retries, exponential backoff, and fallback across models for rate limits or outages.

Hand tasks from Claude Code, Cursor or Codex to a personal agent through a folder of markdown notes, and read the reply back. Runs on your computer: no hosted service, no account, no telemetry. Eight tools: send, status, list, read, wait, rules and the agent's inbox. Optional email, Telegram or Slack heads-up (outgoing only, off by default). Refuses requests that look like passwords or keys.

Enables persistent SQLite-backed tasks, recorded parent/child agent relationships, workflow groups, and lead-mediated conversation snapshots and navigation requests through compatible ChatGPT/Codex hosts.

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.

A production-grade MCP server for integrating RAG into AI agents, supporting multiple vector databases with enterprise security and dynamic tool selection.

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 interaction with Telnyx's telephony, messaging, and AI assistant APIs to manage phone numbers, send messages, make calls, and create AI assistants. Includes webhook support for real-time event handling and comprehensive tools for voice, SMS, cloud storage, and embeddings.

A universal Model Context Protocol implementation that serves as a semantic layer between LLMs and 3D creative software, providing a standardized interface for interacting with various Digital Content Creation tools through a unified API.

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.

Drive your real Chrome from any coding agent (pi, Claude Code, Codex) via a token-paired, localhost-only extension: navigate, click, eval JS, read page text, screenshot. Bundled with AgentDeck, a 2x2 web-terminal cockpit for running multiple coding agents side by side.

An MCP server that lets agents act as the person who added them, giving them identity, shared context (data, documents, goals, calendar, skills), and a place to publish apps and pages behind sign-in. It also brokers access to models, data APIs and other tools' MCP servers through one key, with consent prompts, per-person access checks and encrypted credentials as guardrails.

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.

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.

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.

Enables multiple Claude agents to share and curate markdown memory files in versioned S3 storage, with conflict-safe reads and writes, attribution, search, and session trace summaries.

Enables real-time communication and orchestration of multiple AI agents with a web dashboard for monitoring agent activities, tasks, and artifacts.

Enables local multi-agent Codex collaboration through a SQLite task graph, atomic task claiming and leases, isolated Git worktrees, append-only events and messages, and a local web Kanban board.