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

Model Context Protocol

anthropic.com

Post reply on HN
Print view View original

71–80 of 283 posts

Re: Model Context Protocol

#71

Post by jspahrsummers »

singularity2001 wrote: post #50
somnium_sn wrote: post #3

@jspahrsummers and I have been working on this for the last few months at Anthropic. I am happy to answer any questions people might have.

Is there any way to give a MCP server access for good? Trying out the demo it asked me every single time for permission which will be annoying for longer usage.

We do want to improve this over time, just trying to find the right balance between usability and security. Although MCP is powerful and we hope it'll really unlock a lot of potential, there are still risks like prompt injection and misconfigured/malicious servers that could cause a lot of damage if left unchecked.

Re: Model Context Protocol

#72

Post by drdaeman »

instagary wrote: post #14
somnium_sn wrote: post #3

@jspahrsummers and I have been working on this for the last few months at Anthropic. I am happy to answer any questions people might have.

What is a practical use case for this protocol?

Zed editor had just announced support for MSP in some of their extensions, publishing an article showing some possible use cases/ideas: https://zed.dev/blog/mcp

Re: Model Context Protocol

#73

Post by simonw »

bentiger88 wrote: post #58

One thing I dont understand.. does this rely on vector embeddings? Or how does the AI interact with the data? The example is a sqllite satabase with prices, and it shows claude being asked to give the average price and to suggest pricing optimizations. So does the entire db get fed into the context? Or is there another layer in between. What if the database is huge, and you want to ask the AI for the most expensive o…

Vector embeddings are entirely unrelated to this.

This is about tool usage - the thing where an LLM can be told "if you want to run a SQL query, say select * from repos - the code harness well then spot that tag, run the query for you and return the results to you in a chat message so you can use them to help answer a question or continue generating text".

Re: Model Context Protocol

#74

Post by simonw »

cma wrote: post #70
orliesaurus wrote: post #61

Earlier quoted context omitted.

it doesnt feed the whole DB into the context, it gives Claude the option to QUERY it directly

It never accidentally deletes anything? Or I guess you give it read only access? It is querying it through this API and some adapter built for it, or the file gets sent through the API, they recognize it is sqllite and load it on their end?

It can absolutely accidentally delete things. You need to think carefully about what capabilities you enable for the model.

Re: Model Context Protocol

#75

Post by bionhoward »

I love how they’re pretending to be champions of open source while leaving this gem in their terms of use

“”” You may not access or use, or help another person to access or use, our Services in the following ways: … To develop any products or services that compete with our Services, including to develop or train any artificial intelligence or machine learning algorithms or models. “””

Re: Model Context Protocol

#76

Post by deet »

orliesaurus wrote: post #38

Are there any other Desktop apps other than Claude's supporting this?

My team and I have a desktop product with a very similar architecture (a central app+UI with a constellation of local servers providing functions and data to models for local+remote context)

If this protocol gets adoption we'll probably add compatibility.

Which would bring MCP to local models like LLama 3 as well as other cloud providers competitors like OpenAI, etc

Re: Model Context Protocol

#77

Post by jascha_eng »

somnium_sn wrote: post #65
jascha_eng wrote: post #53

Earlier quoted context omitted.

Will you also create some info on how other LLM providers can integrate this? So far it looks like it's mostly a protocol to integrate with anthropic models/desktop client. That's not what I thought of when I read open-source. It would be a lot more interesting to write a server for this if this allowed any model to interact with my data. Everyone would benefit from having more integration and you (anthropic) still w…

Note that both Sourcegraph's Cody and the Zed editor support MCP now. They offer other models besides Claude in their respective application. The Model Context Protocol initial release aims to solve the N-to-M relation of LLM applications (mcp clients) and context providers (mcp servers). The application is free to choose any model they want. We carefully designed the protocol such that it is model independent.

LLM applications just means chat applications here though right? This doesn't seem to cover use cases of more integrated software. Like a typical documentation RAG chatbot.

Re: Model Context Protocol

#78

Post by pants2 »

This is awesome. I have an assistant that I develop for my personal use and integrations are the more difficult part - this is a game changer.

Now let's see a similar abstraction on the client side - a unified way of connecting your assistant to Slack, Discord, Telegram, etc.

Re: Model Context Protocol

#79

Post by loeber »

bionhoward wrote: post #75

I love how they’re pretending to be champions of open source while leaving this gem in their terms of use “”” You may not access or use, or help another person to access or use, our Services in the following ways: … To develop any products or services that compete with our Services, including to develop or train any artificial intelligence or machine learning algorithms or models. “””

OpenAI and many other companies have virtually the same language in their T&Cs.

Re: Model Context Protocol

#80

Post by orliesaurus »

deet wrote: post #76
orliesaurus wrote: post #38

Are there any other Desktop apps other than Claude's supporting this?

My team and I have a desktop product with a very similar architecture (a central app+UI with a constellation of local servers providing functions and data to models for local+remote context) If this protocol gets adoption we'll probably add compatibility. Which would bring MCP to local models like LLama 3 as well as other cloud providers competitors like OpenAI, etc

would love to know more
Post reply on HN