YuzeHao2023/Awesome-MCP-Servers

A curated list of Model Context Protocol (MCP) servers

What it solves

This project provides a centralized, community-curated directory of Model Context Protocol (MCP) servers. MCP is an open standard that allows AI models to securely connect to external data, tools, and local resources, solving the problem of fragmented integrations by providing a standardized way for AI to interact with software.

How it works

The repository acts as a comprehensive index of available MCP servers, categorized by function (such as databases, file systems, or cloud platforms). It helps users discover implementations that allow their AI clients—like Claude Desktop, Cursor, or Zed—to perform tasks like querying databases, searching the web, or managing files. It also includes utilities for installing and managing these servers.

Who it’s for

This list is for developers and AI power users who want to extend the capabilities of their AI assistants by connecting them to specific tools, APIs, or local data sources. It is also a resource for those building their own MCP-compatible tools.

Highlights

  • Contains a massive, crawler-compiled list of approximately 6,000 potential MCP entries.
  • Organizes servers into clear categories like File Systems, Databases, Cloud Platforms, and Workflow Automation.
  • Provides a dedicated section for official, vendor-maintained integrations marked with a star (⭐).
  • Includes a vital security warning regarding the risks of running MCP servers, such as potential unauthorized code execution or data exposure.
  • Features a collection of CLI tools and utilities to simplify the discovery and installation of MCP servers.

Related

  • Project
    pikpikcu/airecon

    An autonomous penetration testing agent that uses LLMs to drive a Kali Linux sandbox and Caido proxy to automate the RECON-ANALYSIS-EXPLOIT-REPORT pipeline.

  • Project
    apify/mcpc

    mcpc is a universal command‑line client for the Model Context Protocol (MCP). It maps every MCP operation—tools, prompts, resources, tasks, skills, OAuth authentication, and even experimental x402 payments—into intuitive shell commands. Designed for AI agents and developers, it lets you inspect, debug, and script MCP workflows using standard Unix tools (e.g., jq, xargs). Features include persistent named sessions, progressive tool discovery via `grep`, JSON‑only output mode, secure OAuth 2.1 storage (OS keychain or protected file), AI sandboxing, and lightweight cross‑platform support.

  • Project
    MaxBittker/rs-sdk

    A research-oriented framework for developing and testing autonomous agents within a simulated MMO environment, designed for studying goal-directed program synthesis and multi-agent systems.

  • Project
    jonwiggins/optio

    Optio is an open‑source, self‑hosted platform that lets you orchestrate AI coding agents, scheduled jobs, and interactive terminal sessions from a single web or mobile UI. It runs on Kubernetes (or locally), supports 14 trigger types (GitHub, Slack, PagerDuty, etc.), lets you pick LLM providers (Claude, OpenAI, Gemini, etc.) or plain shell commands, and offers persistent agents, secure credential scoping, and native iOS/Android apps. MIT licensed.