Awesome Agent Protocol
AI Agent Protocol ๐ค-๐ค: Three Core Pillars of Agent Technology โ Agent connecting to the external world (MCP), Agent-to-Agent collaboration (A2A), and Agent interacting with humans (ACP).
Install
$ agentstack add mcp-yuan-manx-awesome-agent-protocol โ scanned ยท โ verified, works with Claude Code, Cursor, and more.
Security review
โ PassedNo issues found. Passed automated security review. ยท v0.1.0 How review works โ
- โ Prompt-injection patterns
- โ Secret / credential exfiltration
- โ Dangerous shell & filesystem operations
- โ Untrusted network calls
- โ Known-malicious package signatures
What it can access
- โ Network access No
- โ Filesystem access No
- โ Shell / process execution No
- โ Environment & secrets No
- โ Dynamic code execution No
From automated source analysis of v0.1.0. โUsedโ means the capability is present in the source โ more access means more to trust, not that itโs unsafe.
Verified badge
Passed review? Show it. Paste this badge into your README, it links to the public security report.
Links to your public security report.[](https://agentstack.voostack.com/security/report/mcp-yuan-manx-awesome-agent-protocol) Reliability & compatibility
Declared compatibility
Compatibility is declared by the source manifest. End-to-end runtime verification is coming, see below.
We're building live execution health for every listing: tool-call success rate, median latency, uptime, and last-checked timestamps, measured, not self-reported. It isn't live yet, so we don't show numbers we can't stand behind.
How agent discovery & health will work โAbout
Awesome Agent Protocol ๐ค-๐ค
AI Agent Protocol: Three Core Pillars of Agent Technology โ Agent connecting to the external world (MCP), Agent-to-Agent collaboration (A2A), and Agent interacting with humans (ACP).
English / [็ฎไฝไธญๆ](README_CN.md)
Contents
- [MCP (Model Context Protocol) - Agent Connecting to External World](#mcp-model-context-protocol---agent-connecting-to-external-world)
- [MCP Protocols](#mcp-protocols)
- [SDKs/Libraries](#sdkslibraries)
- [Tools](#tools)
- [Applications](#applications)
- [A2A (Agent-to-Agent) - Agent Collaboration](#a2a-agent-to-agent---agent-collaboration)
- [A2A Protocols](#a2a-protocols)
- [Multi-Agent Frameworks](#multi-agent-frameworks)
- [Coordination Tools](#coordination-tools)
- [ACP (Agent Client Protocol) - Agent Client Protocol](#acp-agent-client-protocol---agent-client-protocol)
- [ACP Protocols](#acp-protocols)
- [Desktop Apps](#desktop-apps)
- [Web Apps](#web-apps)
- [Mobile Apps](#mobile-apps)
MCP (Model Context Protocol) - Agent Connecting to External World
MCP is a standard protocol for connecting Agents to the external world, enabling Agents to access file systems, databases, APIs, and other resources.
MCP Protocols
- Model Context Protocol - Official MCP protocol documentation and specification by Anthropic
- mcp - Official MCP implementation and SDK
SDKs/Libraries
- mcp-python - Python SDK for creating MCP servers
- mcp-typescript - TypeScript/JavaScript SDK
- mcp-go - Go SDK
Tools
- mcp-cli - MCP command-line tool
- mcp-inspector - MCP server inspection tool
Applications
- Claude Desktop - Claude desktop client with MCP support
- openEuler Intelligence - Intelligent LLM platform with MCP service management
- Operit AI - Android AI assistant with full MCP support
A2A (Agent-to-Agent) - Agent Collaboration
Communication protocols, collaboration frameworks, and coordination tools between Agents.
A2A Protocols
- Agent2Agent (A2A) - Agent2Agent (A2A) is an open protocol enabling communication and interoperability between opaque agentic applications.
- Agent2Agent (A2A) Protocol - An open protocol enabling communication and interoperability between opaque agentic applications.
Multi-Agent Frameworks
- AutoGen - Microsoft multi-agent conversation framework
- LangGraph - LangChain's multi-agent graph framework
- CrewAI - Collaborative multi-agent framework
- MetaGPT - Software company multi-agent system
- ChatDev - Virtual software development company
- Agents - An Open-source Framework for Autonomous Language Agents
Coordination Tools
- AgentOps - Agent observability and debugging tool
- LangSmith - LangChain's Agent debugging platform
- AgentBoard - Multi-agent system monitoring dashboard
ACP (Agent Client Protocol) - Agent Client Protocol
Client protocols and applications for Agent interaction with humans.
ACP Protocols
- acpx - Headless CLI client for stateful Agent Client Protocol (ACP) sessions.
Desktop Apps
- IntelliBar - macOS menu bar AI assistant
- MacGPT - Native macOS AI app
- Chatbox - Cross-platform AI chat client
- SwiftChat - Cross-platform AI chat app built with React Native
Web Apps
- ChatGPT - OpenAI ChatGPT web version
- Claude - Anthropic Claude web version
- Chatbot UI - Open-source AI chat interface
- ChatGPT Next Web - Cross-platform ChatGPT client
Mobile Apps
- Petey - iOS and watchOS AI app
- ChatGPT Android - ChatGPT Android client
- ETOS LLM Studio - watchOS and iOS flagship AI client
- xhai Browser - Android desktop management & AI browser with DeepSeek as default AI engine
Contributing
Contributions welcome! Please see the [Contributing Guide](CONTRIBUTING.md) for how to participate.
License
[CC0-1.0](license)
Source & license
This open-source MCP server is cataloged on AgentStack and links to its original source โ we do not rehost the code.
- Author: Yuan-ManX
- Source: Yuan-ManX/awesome-agent-protocol
- License: MIT
Install and usage instructions live in the source repository linked above.
Reviews
No reviews yet, be the first.
Write a review
Versions
- v0.1.0 Imported from the upstream source.