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

171–180 of 283 posts

Re: Model Context Protocol

#171

Post by epistasis »

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.

I read through several of the top level pages, then SQLite, but still had no idea what was meant by "context" as it's a highly ambiguous word and is never mentioned with any concrete definition, example, or scope of capability that it is meant to imply.

After reading the Python server tutorial, it looks like there is some tool calling going on, in the old terminology. That makes more sense. But none of the examples seem to indicate what the protocol is, whether it's a RAG sort of thing, do I need to prompt, etc.

It would be nice to provide a bit more concrete info about capabilities and what the purposes is before getting into call diagrams. What do the arrows represent? That's more important to know than the order that a host talks to a server talks to a remote resource.

I think this is something that I really want and want to build a server for, but it's unclear to me how much more time I will have to invest before getting the basic information about it!

Re: Model Context Protocol

#173

Post by geelen »

Aivean wrote: post #146
jspahrsummers wrote: post #15

Earlier quoted context omitted.

Already available in the latest at https://claude.ai/download !

I'm on the latest Claude desktop for mac (0.7.1, pro plan). Can't see the mcp icon neither in the app nor in the web. How to troubleshoot?

Same issue here. Is it geolocked maybe?

Re: Model Context Protocol

#175

Post by somnium_sn »

epistasis wrote: post #171
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.

I read through several of the top level pages, then SQLite, but still had no idea what was meant by "context" as it's a highly ambiguous word and is never mentioned with any concrete definition, example, or scope of capability that it is meant to imply. After reading the Python server tutorial, it looks like there is some tool calling going on, in the old terminology. That makes more sense. But none of the examples s…

Thank you. That’s good feedback.

The gist of it is: you have an llm application such as Claude desktop. You want to have it interact (read or write) with some system you have. MCP solves this.

For example you can give the application the database schema as a “resource”, effectively saying; here is a bunch of text, do whatever you want with it during my chat with the llm. Or you can give the application a tool such as query my database. Now the model itself can decide when it wants to query (usually because you said: hey tell me what’s in the accounts table or something similar).

It’s “bring the things you care about” to any llm application with an mcp client

Re: Model Context Protocol

#177

Post by jvalencia »

stanleydrew wrote: post #149
jvalencia wrote: post #106

I don't trust an open source solution by a major player unless it's published with other major players. Otherwise, the perverse incentives are too great.

What risk do you foresee arising out of perverse incentives in this case?

Changing license terms, aggressive changes to the API to disallow competition, horrendous user experience that requires a support contract. I really don't think there's a limit to what I've seen other companies do. I generally trust libraries that competitors are maintaining jointly since there is an incentive toward not undercutting anyone.

Re: Model Context Protocol

#178

Post by TeMPOraL »

somnium_sn wrote: post #175
epistasis wrote: post #171

Earlier quoted context omitted.

I read through several of the top level pages, then SQLite, but still had no idea what was meant by "context" as it's a highly ambiguous word and is never mentioned with any concrete definition, example, or scope of capability that it is meant to imply. After reading the Python server tutorial, it looks like there is some tool calling going on, in the old terminology. That makes more sense. But none of the examples s…

Thank you. That’s good feedback. The gist of it is: you have an llm application such as Claude desktop. You want to have it interact (read or write) with some system you have. MCP solves this. For example you can give the application the database schema as a “resource”, effectively saying; here is a bunch of text, do whatever you want with it during my chat with the llm. Or you can give the application a tool such as…

Or, in short: it's (an attempt to create) a standard protocol to plug tools to LLM app via the good ol' tools/function calling mechanism.

It's not introducing new capabilities, just solving the NxM problem, hopefully leading to more tools being written.

(At least that's how I understand this. Am I far off?)

Re: Model Context Protocol

#180

Post by jihadjihad »

bluerooibos wrote: post #169

Awesome! In the "Protocol Handshake" section of what's happening under the hood - it would be great to have more info on what's actually happening. For example, more details on what's actually happening to translate the natural language to a DB query. How much config do I need to do for this to work? What if the queries it makes are inefficient/wrong and my database gets hammered - can I customise them? How do I ensu…

One thing I am having a hard time wrapping my head around is how to reliably integrate business logic into a system like this. Just hook up my Rails models etc. and have it use those?

Let’s say I’ve got a “widgets” table and I want the system to tell me how many “deprecated widgets” there are, but there is no convenient “deprecated” flag on the table—it’s defined as a Rails scope on the model or something (business logic).

The DB schema might make it possible to run a simple query to count widgets or whatever, but I just don’t have a good mental model of how these systems might work with “business logic” type things.

Post reply on HN