Summary
We have a dedicated page which captures various frameworks and tools for building Agentic AI applications.
The main building block for such agentic LLM workflow applications is the integration to various data sources and systems to exchange data. This post lists and summarizes an exiting data integration protocols for modern agentic applications.
Protocols
MCP
Model Context Protocol or MCP is an open source protocol, which aims to standardize how applications provide the context to LLMs in agentic workflows.
Developed and maintained by Anthropic - AI research and product company.
A2A
Agent2Agent or A2A protocol is an open source protocol for agentic workflows, which defines the standard for agent to agent data exchanges.
Its aim to complement MCP protocol with the focus on the multi agent systems, where agents interact with each other.
Proposed, developed and maintained by Google.
ACP
Agent Communication Protocol or ACP is an open protocol for communication between AI agents. As an alternative to Agent2Agent protocol listed above.
Notes
New protocols are being discussed and rolled out in the industry. Let me know if I'm missing some on this list and if you would recommend additional protocols to be added to the list.