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

131–140 of 293 posts

Re: The Agent2Agent Protocol (A2A)

#131

Post by maxwellg »

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.

I wasn't around for WSDL so please correct me if I am wrong - but the main weakness of WSDL was that no applications were able to take advantage of dynamic service and method discovery? A service could broadcast a WSDL but something needed to make use of it, and if you're writing an application you might as well just write against a known API instead of an unknown one. LLMs promise to be the unstructured glue that can take advantage of newly-discovered methods and APIs at runtime.

Re: The Agent2Agent Protocol (A2A)

#132

Post by matchagaucho »

If robots.txt is an exclusion file, I can't help but wonder if we just need an agents.json inclusion file in the root to get a "standard" started.

A2A looks like a typical enterprise, authenticated, strict DTD style spec.

Agents acting on behalf of consumers need a simple file that describes: 1) What services are provided 2) What tools are available and how to use them

Agent behavior and actions should happen in latent space. The format of any spec is almost meaningless, as long as it's self describing and conveys those 2 points.

Re: The Agent2Agent Protocol (A2A)

#134

Post by polynomial »

behnamoh wrote: post #46
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/

It seems the industry as a whole just forgot about prompt injection attacks because RLHF made models really good at rejecting malicious requests. Still, I wonder if there have been any documented cases of prompt attacks.

While RLHF has indeed been very effective at countering one-shot prompt injection attacks, it's not much of a bullwark against persistent jailbreaking attempts. This is not to argue a point but rather to suggest jailbreaks are still very much a thing, even if they are no longer as simple as "ignore your ethics"

Re: The Agent2Agent Protocol (A2A)

#136

Post by gatienboquet »

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.

XHTML 2.0,WML,SOAP, APPN,WAP...for each new technology there's thousands of failed protocol.

Re: The Agent2Agent Protocol (A2A)

#137

Post by zellyn »

laichzeit0 wrote: post #12
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…

Take a look at the samples: https://google.github.io/A2A/#/documentation

Oh, that's really nice. I'd also like to see what syntax the LLM uses to _trigger_ these calls, and what prompt is sent to the LLM to tell it how to do that.

I should probably just go read Goose's code…

Re: The Agent2Agent Protocol (A2A)

#138

Post by abshkbh »

simonw wrote: post #121

OK, I have to ask: isn't this agents to agents idea kind of Science Fiction? I absolutely get the value of LLMs calling tools and APIs. I still don't see much value in LLMs calling other LLMs. Everyone gets really excited about it - "langchain" named their whole company over the idea of chaining LLMs together - but aside from a few niche applications (Deep Research style tools presumably fire off a bunch of sub-promp…

Morden software consists of separation of responsibilities between services and a higher plane orchestrating the data flow for business logic.

If you believe there is value in fuzzy tasks being done by LLMs then from that it follows that having separate "agent" services with a higher order orchestrator would be required. Each calling LLMs on their own inside.

Re: The Agent2Agent Protocol (A2A)

#139

Post by zellyn »

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…

Yeah, I got that from reading the Ghidra MCP (very instructive, strong recommend), but I'm curious what the LLM needs to output to call it. I should go read Goose's code or instrument it or something…

Re: The Agent2Agent Protocol (A2A)

#140

Post by zellyn »

mlenhard wrote: post #76
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…

I was in the same boat in regards to trying to find the actual JSON that was going over the wire. I ended up using Charles to capture all the network requests. I haven't finished the post yet, but if you want to see the actual JSON I have all of the request and responses here https://www.catiemcp.com/blog/mcp-transport-layer/

Oh, that's really nice. Did you capture the responses from the LLM. Presumably it has some kind of special syntax in it to initiate a tool call, described in the prompt? Like TOOL_CALL or something…
Post reply on HN