"Philips Hue" matching MCP servers:

A Model Context Protocol server that enables AI assistants to control Philips Hue smart lighting systems through natural language commands.

Enables agents to search a lightweight catalog, inspect permissions, lazily start trusted MCP servers, and call child tools without keeping all schemas in context. It also loads approved skills on demand and routes third-party additions through a human approval queue.

A meta-MCP server that acts as a single connection point to lazily spawn and proxy multiple MCP servers, reducing context bloat and process overhead.

Provides a workspace-safe, read-only bridge between browser-based AI planning/review and local coding agents, enabling structured plan, execution summary, and review handoffs without granting shell, file write, or Git push access.

A hub server that connects to and manages other MCP servers, allowing users to bypass Cursor's 40-tool limit and reduce AI mistakes by hiding infrequently used tools.

Enables users to curate a personal toolbox of tools and connect to Claude or Cowork with a single login, while OAuth scopes filter which MCP tools are available and all calls are recorded for audit.

MCP hub server that aggregates tools from multiple domain packages into a single globally-available interface.

Enables AI agents to coordinate open projects by registering, creating and claiming tasks, submitting and reviewing work, electing coordinators, and chatting in a shared lobby.

Aggregates dozens of pre-built connectors into one OpenAI-compatible endpoint for AI clients, with a web UI for installing, configuring, monitoring, and managing them.

Enables local workspace management and status checks through MCP tools over an HTTP endpoint, allowing DeepSeek Harness to interact with the platform.

A meta-MCP server that uses Llama AI as an orchestrator to intelligently route requests and coordinate workflows across multiple MCP services like Stripe, GitHub, and databases. Enables complex multi-service operations with AI-driven decision making and parallel execution capabilities.

Lets multiple agent clients running on one machine or across a LAN register identities, designate one as master and the rest as subagents, and coordinate work through task dispatch, claim, progress reporting, messaging, rooms, and a shared versioned blackboard backed by SQLite. Supports both stdio with a shared database and Streamable HTTP so many clients can connect to a single hub.

Hosts multiple Model Context Protocol servers (fetch, memory, GitHub, Postgres, utils) behind a single authenticated gateway, giving AI agents instant access via one Bearer token.

Enables coordinating two coding agents through a shared SQLite task pool with an explicit review workflow, allowing agents to query, claim, submit, review, and approve or reject tasks while enforcing reviewer and iteration safeguards.

MCP server for universal multi-agent communication, enabling agents to register, send/receive messages, manage tasks, and coordinate via role-based routing with project isolation.

Privacy-first local MCP hub for coordinating multiple AI providers from Claude Code, supporting local Ollama seats and cloud providers with safety routing.

A TypeScript gateway for Model Context Protocol servers that aggregates multiple downstream MCP servers, providing tool discovery, routing, smart search, and recommendations.

A universal MCP hub that connects any AI agent to any tool, enabling agent interoperability with 50+ pre-built tools, custom tool creation, and tool discovery.

A local message broker for AI CLI agents, enabling multiple agent sessions to communicate, send tasks, and share results through a single HTTP endpoint.

Enables AI sessions like Claude, Cowork, and Claude Code to pass tasks and replies between each other through per-session mailboxes, and to keep a shared knowledge base of notes that every session can read, search, and update. Runs as a self-hosted Cloudflare Worker with D1 storage, so all data stays in the user's own account.