"Overview and Applications of Mixture of Experts in Machine Learning" matching MCP servers:

An MCP server adapter that allows LLM agents to autonomously play World of ClaudeCraft by wrapping the game's headless environment as MCP tools for state reading and action execution.

Structured reasoning MCP server that decomposes problems into atomic steps (premise, reasoning, hypothesis, verification, conclusion) with confidence scoring, live visualization, and approval feedback.

Shrimp Task Manager is a task tool built for AI Agents, emphasizing chain-of-thought, reflection, and style consistency. It converts natural language into structured dev tasks with dependency tracking and iterative refinement, enabling agent-like developer behavior in reasoning AI systems.

A multi-agent orchestration system that enables multiple Claude instances to collaborate through a centralized hub with a shared workspace and real-time communication. It features integrated task management, role assignment, and persistent memory to facilitate complex, synchronized agent workflows.

Implements the Chain of Draft reasoning approach to generate minimalistic intermediate reasoning outputs while solving tasks, significantly reducing token usage while maintaining accuracy.

An MCP server that uses Groq's API to expose raw chain-of-thought tokens from Qwen's qwq model, enabling LLMs to think step-by-step before responding.

A Model Context Protocol (MCP) server that enables structured multi-path investigations using a Tree of Thoughts approach.

Transforms prompts into Chain of Draft (CoD) or Chain of Thought (CoT) format to enhance LLM reasoning quality while reducing token usage by up to 92.4%, supporting multiple LLM providers including Claude, GPT, Ollama, and local models.

AoT MCP server enables AI models to solve complex reasoning problems by decomposing them into independent, reusable atomic units of thought, featuring a powerful decomposition-contraction mechanism that allows for deep exploration of problem spaces while maintaining high confidence in conclusions.

Write and mail personalized funny booklets via an AI agent. Allows agents to commission custom 16-page print gifts for users.

An MCP relay that adds a use_jev tool to every connected server, letting the Jev model autonomously select and execute tool calls while the calling model supplies any required text values. It enables agents to delegate multi-step tool use across all configured MCP servers through a single unified interface.

Implements the Tree of Thoughts framework for structured reasoning and decision tree exploration, enabling LLMs to explore multiple reasoning paths, evaluate them, and backtrack.

Enables autonomous learning from interactions through pattern recognition and machine learning techniques. Continuously improves performance by analyzing tool usage, providing predictive suggestions, and sharing knowledge across MCP servers.

Enables AI agents to learn from their work by recording tasks, extracting patterns, detecting mistakes, and proactively surfacing insights, all using the agent's own model through a cooperative intelligence pattern.

Enables AI agents to autonomously request services from other specialized agents and compensate them via x402 micropayments. Demonstrates a Machine-to-Machine economy using A2A protocol for agent communication, MCP for context management, and blockchain-based payments on Base network.

Enables building and evaluating LangGraph agents over a protocol-level MCP server to measure failure rates across four agent topologies.

Give any LLM agent a real Android or iPhone. 62 MCP tools: tap, swipe, type, screenshot, screen-tree reading, app launch, camera, TTS, crash reports, batched execution. Android via ADB, iPhone via WebDriverAgent, on-device inference, Docker+KVM emulators. Works with Claude Code, Cursor, LangChain, LlamaIndex, and any MCP client. MIT.

Enables AI assistants to control Discord servers with 93 tools for server management, moderation, voice TTS, AI chat via OpenRouter, and World of Warships stats lookup through the Model Context Protocol.

Enables Claude Code instances to discover each other on a local machine and exchange messages instantly, with a broker that coordinates triage and delegation across a peer mesh.

Provides a hand-written MCP server integrated with a LangGraph agent to benchmark multiple agent topologies and measure their failure rates.