Discover Awesome MCP Servers

Compendium

MCP server that minimizes LLM token usage by compressing, summarizing, filtering, chunk-referencing, and pruning large context before it reaches the model, with heuristic or local-SLM smart actions, caching, and token counting.

Todo MCP

A demo MCP server that exposes a shared todo list as tools over Streamable HTTP, enabling agents to list, add, complete, and delete todos alongside a Next.js web UI.

MCP Riot Server

A community-developed Model Context Protocol server that integrates with the Riot Games API to provide League of Legends data, enabling AI assistants to retrieve player information, ranked stats, champion mastery, and match summaries through natural language queries.

AWS Amplify Documentation MCP Server

Enables searching AWS Amplify documentation using natural language queries with advanced search syntax, smart ranking, and generation selection.

omniwatchguard-mcp

Enables users to manage OmniWatchGuard website monitors and alerts via natural language. Supports listing, creating, updating, pausing, resuming, and deleting monitors, plus reviewing recent notifications across channels.

Company MCP Server - Google Workspace Integration

Enables Claude to interact with Google Workspace services including Gmail, Drive, Sheets, Docs, and Calendar. Provides comprehensive tools for reading, creating, and managing emails, files, spreadsheets, documents, and calendar events with built-in safety controls and audit logging.

AXT-MCP

A Model Context Protocol service registry and connector framework that enables seamless integration with multiple services and models through a standardized API interface. Provides an extensible architecture for custom service adapters, API integrations, and model registries.

IMS MCP Server

Exposes the Integrated Memory System (IMS) capabilities, including session management, memory storage, and RAG-based context search, via the Model Context Protocol. It allows MCP-aware clients to interact with IMS backends to maintain long-term memory and context across sessions.

MCP Agent Skills Server

A production-ready MCP server that equips AI agents with dynamic, persistent, and executable skills. It enables secure script execution and progressive disclosure to reduce context window usage.

repo-explorer-mcp

Enables LLM-driven repository exploration by exposing an explore_repository tool over stdio, using codebase memory and ripgrep/rtk search to navigate and analyze codebases.

IGDS Storybook MCP Server

MCP server for the Israeli Government Design System (IGDS), providing tools to query Storybook component data and Zeroheight design documentation across Angular, React, and Core-Web frameworks.

agent-vision

A lightweight MCP server that enables text agents to analyze images and videos using OpenAI-compatible vision models, with tools for image analysis and video frame extraction.

AWS Terraform MCP Server

A containerized Model Context Protocol server that enables using natural language to develop AWS infrastructure with Terraform, offering best practices guidance, security scanning with Checkov, and access to AWS provider documentation.

AI Fuzz Testing MCP Server

A Model Context Protocol server for LLM fuzzing and testing, providing secure access to multiple AI providers through a standardized interface.

Modular RAG MCP Server

A modular RAG framework exposing MCP tools for hybrid document search, enabling AI assistants to query private knowledge bases with multimodal support and full observability.

LatentContext MCP Server

A session-scoped memory layer for LLMs that enables AI assistants to explicitly store and retrieve notes, decisions, and context within a single conversation, ensuring focus without cross-session data contamination.

SMNGRP05 Thief MCP Server

Runs a decentralized thief agent for a peer-to-peer cops-and-robbers game, using FastMCP to exchange moves and messages with a police agent while employing Bayesian belief and credibility-based bluffing strategies.

vision-bridge-mcp

Enables text-only AI agents to analyze and transcribe images via Gemini, letting them understand screenshots, diagrams, and photos without manual copying.

AetherTech MCP Server

A production-ready MCP server offering text analysis tools, an in-memory key-value store, and system info resources with support for both stdio and HTTP transports.

yt-music-mcp

MCP server for YouTube Music that enables searching songs and artists, managing playlists, and authenticating via Google OAuth, using STDIO transport.

Rancher MCP Server

A Model Context Protocol (MCP) server that exposes the Rancher Manager v2.x API to LLM clients.

uk-ai-bill-compliance-mcp

MCP server for UK AI Bill 2026 compliance, implementing a 5-principles framework (Safety, Transparency, Fairness, Accountability, Contestability) to help audit and classify AI systems.

AACT Clinical Trials MCP Server

Provides AI assistants with direct query access to the AACT (Aggregate Analysis of ClinicalTrials.gov) database, allowing structured retrieval and analysis of clinical trial data.

DeepSeek Reasoner MCP

「順序立てて考える」MCPの強化版

BundlerMCP

Enables agents to query information about gems in a Ruby project's Gemfile, including source code and metadata.

EmailInABox MCP Server

Enables private email hosting provisioning and management via MCP tools, including domain deployment, mailbox creation, DNS configuration, tracked email sending, and analytics.

cro_pe_cadastro

Read-only MCP server for querying the Pernambuco Regional Council of Dentistry (CRO-PE) registration database via official sources, enabling verified professional status checks through natural language.

Hostodo MCP

Manage Hostodo VPS infrastructure from MCP clients and AI agents with scoped tokens and audit logs.

tplink-omada-mcp

Exposes TP-Link Omada controller APIs to AI copilots, enabling listing of sites, devices, and clients, and executing arbitrary Omada API calls via natural language.

aws-safe-mcp

A read-only MCP server for safe, structured investigation of AWS serverless resources, providing curated tools for tracing dependencies, permissions, and failures without exposing raw SDK access.