[HN Gopher] Hassabis Says Google DeepMind to Support Anthropic's...
___________________________________________________________________
Hassabis Says Google DeepMind to Support Anthropic's MCP for Gemini
and SDK
Author : thoughtpeddler
Score : 137 points
Date : 2025-04-10 17:34 UTC (4 days ago)
(HTM) web link (techcrunch.com)
(TXT) w3m dump (techcrunch.com)
| omneity wrote:
| I hope they also improve their JSONSchema support for structured
| output and tool calling. Currently it has many limitations
| compared to OpenAI's, for example it doesn't support
| "additionalProperties" which eliminates an entire class of use
| cases and makes it immediately incompatible with many MCP
| servers.
|
| Marketing the API as OpenAI-compatible and then me getting 400s
| when I switch to Gemini leaves a sour taste in the mouth, and
| doesn't make me confident about their MCP support.
| jeswin wrote:
| Given their anti-trust struggles, if Google for some reason
| dominates AI, they'd not want people to bring up anti-competitive
| behavior as a reason for that. Adopting open standards,
| especially open standards conceived outside Google is good for
| everyone including Google. They're well placed - from research to
| hardware to software and data.
|
| They'll also want the industry to rapidly move forward and
| connect data to AI. MCP has momemtum.
| skybrian wrote:
| It's terribly insecure as-is [1]. But so was HTTP. The spec isn't
| final, so hopefully it will improve.
|
| [1] https://blog.sshh.io/p/everything-wrong-with-mcp
| dheera wrote:
| > MCP initially didn't define an auth spec and now that they
| have people don't like it.
|
| Just wrap it in an SSH tunnel or a HTTPS websocket
|
| > MCP servers can run (malicious code) locally.
|
| Just run it in a Docker container
| Sayrus wrote:
| > Just run it in a Docker container
|
| You should probably read the original article in the
| footnotes of OP's article:
| https://equixly.com/blog/2025/03/29/mcp-server-new-
| security-...
|
| While a container will surely protect you from those, it will
| also prevent you using the features implemented by those MCP
| Servers.
| oezi wrote:
| Does MCP solve authentication on user's behalf which stifled
| OpenAI's GPTs?
|
| Tools often need access to data sources but I don't want to hard
| code passwords.
| flakiness wrote:
| I hope Gemini gets a desktop app where MCP servers are more
| useful, but wonder if Google's security posture allows it.
| phildougherty wrote:
| interested to see if Agent-to-Agent protocol duplicates the MCP
| functionality eventually
| behnamoh wrote:
| Well, Google is one of the major investors in Anthropic, so I'm
| not surprised.
| edandersen wrote:
| Are they going to release a Gemini desktop app with MCP support
| so normal people can use it?
| mellosouls wrote:
| Related, discussion on A2A from the other day:
|
| https://news.ycombinator.com/item?id=43631381
|
| _" The Agent2Agent Protocol (A2A)", 279 comments_
| lawrenceyan wrote:
| It doesn't really matter what it is as there are many equally
| good implementations, but whoever sets up the framework first and
| cements usage is likely to guarantee dominance for the
| foreseeable future. Probably into AGI and post.
|
| Model Context Protocol seems good enough to me.
| lovich wrote:
| Is there a good place to read on what the benefit of MCP is? I'm
| behind the curve on this agentic AI shit and am not quite sure
| where to look
| tuyguntn wrote:
| Didn't Google introduce A2A just few days ago? Why Google itself
| is not heavily invested in their protocol?
|
| Smells like a new project in Killed By Google graveyard.
| refulgentis wrote:
| They did.
|
| We're observing a response to takes that A2A meant they weren't
| going to support MCP.
|
| Everyone's got a take and a response these days, it's a nice
| little infinite loop of complaints and that keeps PR kicking.
___________________________________________________________________
(page generated 2025-04-14 23:00 UTC)