Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

The Agent2Agent Protocol (A2A)

developers.googleblog.com

Post reply on HN
Print view View original

81–90 of 293 posts

Re: The Agent2Agent Protocol (A2A)

#81

Post by mycall »

zellyn wrote: post #3

It’s frustratingly difficult to see what these (A2A and MCP) protocols actually look like. All I want is a simple example conversation that includes the actual LLM outputs used to trigger a call and the JSON that goes over the wire… maybe I’ll take some time and make a cheat-sheet. I have to say, the endorsements at the end somehow made this seem worse…

It is quite hard to reliably and consistently connect deterministic systems and goals with nondeterministic compute. I don't know if all of this will ever be exactly what we want.

Re: The Agent2Agent Protocol (A2A)

#82

Post by daxfohl »

zurfer wrote: post #55

My current understanding: MCP - exposes prompts, resources and tools to a host, who can do whatever they like A2A - exposes capability discovery, tasks, collaboration?/chat?, user experience discussions (can we embed an image or or a website?). High-level it makes sense to agree on these concepts. I just wonder if we really need a fully specified protocol? Can't we just have a set of best practices around API endpoin…

That's the first step to creating a protocol. The next step is to formalize it, publish it, and get others to adopt it. That way, it's one less thing for LLMs to hallucinate on. Otherwise everyone has different conventions and LLMs start making stuff up. That's all these are.

Re: The Agent2Agent Protocol (A2A)

#83

Post by maxbaines »

simonw wrote: post #19

I just published some notes on MCP security and prompt injection. MCP doesn't have security flaws in the protocol itself, but the patterns it encourage (providing LLMs with access to tools that can act on the user's behalf while they also may be exposed to text from untrusted sources) are rife for prompt injection attacks: https://simonwillison.net/2025/Apr/9/mcp-prompt-injection/

I agree with your opinion here, not sure we should refer to it as MCP security however, given that 'MCP doesn't have security flaws in the protocol itself'

Re: The Agent2Agent Protocol (A2A)

#84

Post by rvz »

This is disturbing and they are declaring war on you with too many red flags.

> "Today, we’re launching a new, open protocol called Agent2Agent (A2A), with support and contributions from more than 50 technology partners"

Why do you think the majority of the big consultancy firms like McKinsey, KPMG, PwC, Deloitte, Cognizant, Capgemini and Accenture are all here in this round table?

You are on the menu when they arrive to replace you with an agent.

Exhibit A:

> Hiring a software engineer can be significantly simplified with A2A collaboration. Within a unified interface like Agentspace, a user (e.g., a hiring manager) can task their agent to find candidates matching a job listing, location, and skill set.

The recruiter is now an "agent". Not a human. Don't think it isn't going to happen to you because that example targeted recruiters.

The big consultancy firms already have tens of thousands of employees and are ready to try it on them first before recommending to businesses to replace.... you.

Re: The Agent2Agent Protocol (A2A)

#85

Post by skeledrew »

whalesalad wrote: post #52
zellyn wrote: post #3

It’s frustratingly difficult to see what these (A2A and MCP) protocols actually look like. All I want is a simple example conversation that includes the actual LLM outputs used to trigger a call and the JSON that goes over the wire… maybe I’ll take some time and make a cheat-sheet. I have to say, the endorsements at the end somehow made this seem worse…

Agreed. At the end of the day we are talking about RPC. A named method, with known arguments, over the wire. A simple HTTP request comes to mind. But that would just be too easy. Oh wait, that is what all of these are under the hood. We are so cooked. from fastmcp import FastMCP mcp = FastMCP("Demo ") @mcp.tool() def add(a: int, b: int) -> int: """Add two numbers""" return a + b This is an example of fastmcp. Notice…

It's just another layer of abstraction so one doesn't need to think about HTTP at all, which would bring in irrelevant baggage.

Re: The Agent2Agent Protocol (A2A)

#86

Post by fedeb95 »

hliyan wrote: post #63

Are we rediscovering SOA and WSDL, but this time for LLM interop instead of web services? I may be wrong, but I'm starting to wonder whether software engineering degrees should include a history subject about the rise and fall of various architectures, methodologies and patterns.

software engineering IS perpetual rediscovery of the Same.

Re: The Agent2Agent Protocol (A2A)

#87

Post by MattDaEskimo »

zurfer wrote: post #55

My current understanding: MCP - exposes prompts, resources and tools to a host, who can do whatever they like A2A - exposes capability discovery, tasks, collaboration?/chat?, user experience discussions (can we embed an image or or a website?). High-level it makes sense to agree on these concepts. I just wonder if we really need a fully specified protocol? Can't we just have a set of best practices around API endpoin…

Eventually agents from different providers will come into play. It's important to agree on a standard for accurate interoperability.

Ideally, the model providers would then build for the protocol, so the developers aren't writing spaghetti code for every small difference

Re: The Agent2Agent Protocol (A2A)

#88

Post by throwaway-blaze »

mycall wrote: post #81
zellyn wrote: post #3

It’s frustratingly difficult to see what these (A2A and MCP) protocols actually look like. All I want is a simple example conversation that includes the actual LLM outputs used to trigger a call and the JSON that goes over the wire… maybe I’ll take some time and make a cheat-sheet. I have to say, the endorsements at the end somehow made this seem worse…

It is quite hard to reliably and consistently connect deterministic systems and goals with nondeterministic compute. I don't know if all of this will ever be exactly what we want.

Sort of like asking a non-deterministic human to help make changes to an existing computer system. Extends the problems of human team management to our technology systems.

Re: The Agent2Agent Protocol (A2A)

#89

Post by skeledrew »

peab wrote: post #74
whalesalad wrote: post #52

Earlier quoted context omitted.

Agreed. At the end of the day we are talking about RPC. A named method, with known arguments, over the wire. A simple HTTP request comes to mind. But that would just be too easy. Oh wait, that is what all of these are under the hood. We are so cooked. from fastmcp import FastMCP mcp = FastMCP("Demo ") @mcp.tool() def add(a: int, b: int) -> int: """Add two numbers""" return a + b This is an example of fastmcp. Notice…

Yeah, i haven't seen a reason why we can't just use REST. Like, auth is already figured out. The LLMS already have the knowledge of how to call APIs too!

It's like deciding between Assembly or C for some given project.

Re: The Agent2Agent Protocol (A2A)

#90

Post by MattDaEskimo »

rvz wrote: post #84

This is disturbing and they are declaring war on you with too many red flags. > "Today, we’re launching a new, open protocol called Agent2Agent (A2A), with support and contributions from more than 50 technology partners" Why do you think the majority of the big consultancy firms like McKinsey, KPMG, PwC, Deloitte, Cognizant, Capgemini and Accenture are all here in this round table? You are on the menu when they arriv…

This is the reality, unfortunately.

Lots of jobs that focus on communication and data organization are out the window, including recruiters.

Post reply on HN