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

MCP doesn't need tools, it needs code

lucumr.pocoo.org

Post reply on HN
Print view View original

61–70 of 146 posts

Re: MCP doesn't need tools, it needs code

#61

Post by oooyay »

jumploops wrote: post #20

The promise of MCP is that it “connects your models with the world”[0]. In my experience, it’s actually quite the opposite. By giving an LLM a set of tools, 30 in the Playwright case from the article, you’re essentially restricting what it can do. In this sense, MCP is more of a guardrail/sandbox for an LLM, rather than a superpower (you must choose one of these Stripe commands!). This is good for some cases, where y…

In my uneducated experience MCP is nothing more than a really well structured prompt. You can call out tools for the agent or model to use in the instruction prompt, especially for certain project. I define workflows that trigger for certain files being changed in Cursor and usually the model can run uninterrupted for a while.

Re: MCP doesn't need tools, it needs code

#62

Post by pixl97 »

nativeit wrote: post #52
nsonha wrote: post #32

Earlier quoted context omitted.

It's not guardrail, it's guidance. You don't guide a child or an intern with: "here is everything under the sun, just do things", you give them a framework, programming language, or general direction to operate within.

Interns and children didn’t cost $500B.

You're right, they've cost trillions and trillions of dollars and to get any single one up to speed takes the minimum of 18 to 25 years.

500b sounds like a value prop in those regards.

Re: MCP doesn't need tools, it needs code

#63

Post by faangguyindia »

s1mplicissimus wrote: post #26

I tried doing the MCP approach with about 100 tools, but the agent picks the wrong tool a lot of the time and it seems to have gotten significantly worse the more tools I added. Any ideas how to deal with this? Is it one of those unsolvable XOR-like problems maybe?

AI agents can't even remember which files are already in the context, let alone them picking right tool for the job.

Re: MCP doesn't need tools, it needs code

#64

Post by juanviera23 »

stanleydrew wrote: post #43
juanviera23 wrote: post #15

I agree MCP has these flaws, idk why we need MCP servers when LLMs can just connect to the existing API endpoint Started on working on an alternative protocol, which lets agents call native endpoints directly (HTTP/CLI/WebSocket) via “manuals” and “providers,” instead of spinning up a bespoke wrapper server: https://github.com/universal-tool-calling-protocol/python-ut... even connects to MCP servers if you take a loo…

> idk why we need MCP servers when LLMs can just connect to the existing API endpoint Because the LLM can't "just connect" to an existing API endpoint. It can produce input parameters for an API call, but you still need to implement the calling code. Implementing calling code for every API you want to offer the LLM is at minimum very annoying and often error-prone. MCP provides a consistent calling implementation tha…

yupp that's what UTCP does as well, standardizing the tool-calling

(without needing an MCP server that adds extra security vulnerabilities)

Re: MCP doesn't need tools, it needs code

#65

Post by chris222 »

jumploops wrote: post #20

The promise of MCP is that it “connects your models with the world”[0]. In my experience, it’s actually quite the opposite. By giving an LLM a set of tools, 30 in the Playwright case from the article, you’re essentially restricting what it can do. In this sense, MCP is more of a guardrail/sandbox for an LLM, rather than a superpower (you must choose one of these Stripe commands!). This is good for some cases, where y…

I find it’s best to use it to actually give context. Like prompted with a peice of information that the LLM doesn’t know how to look up (such as a link to the status or logs for an internal system), give it a tool to perform the lookup.

Re: MCP doesn't need tools, it needs code

#66

Post by kordlessagain »

As one does, I've built an alternative to MCP: https://ahp.nuts.services

Put GPT5 into agent mode then give it that URL and the token 'linkedinPROMO1' and once it loads the tools tell it to use curl in a terminal (it's faster) and then run the random tool.

This is authenticated at the moment with that token, plus bearer tokens, but I've got the new auth system up and its working. I still have to do the integration with all the other services (the website, auth, AHP and the crawler and OCR engine), so will be a while before all that's done.

Re: MCP doesn't need tools, it needs code

#67

Post by bgwalter »

yxhuvud wrote: post #2

First rule of writing about something that can be abbreviated: First have some explanation so people have an idea of what you are talking about. Either type out what the abbreviation stands for, have an explanation or at least a link to some other page that explain what is going on. EDIT: This has since been fixed in link, so it is outdated.

"MCP" is the new "webscale". It can be used to write philosophical papers about LLMs orchestrating the obliquely owned ontologies of industrial systems, including SCADA systems:

https://arxiv.org/html/2506.11180v1

SCADA systems got famous, because they previously required STUXNET to be hacked. In the future you can just vibe hack them.

Re: MCP doesn't need tools, it needs code

#68

Post by mmargenot »

chuckmcp wrote: post #41
ehnto wrote: post #34

Earlier quoted context omitted.

If you're running one of the popular coding agents, they can run commands in bash which is more or less access to the infinite space of tooling I myself use to do my job. I even use it to troubleshoot issues with my linux laptop that in the past I would totally have done myself, but can't be bothered. Which led to the most relatable AI moment I have encountered: "This is frustrating" - Claude Code thought, after 6 tr…

Even with all of the CLI tools at its disposal (e.g. sed), it doesn’t consistently use them to make updates as it could (e.g. widespread text replacement). Once in a blue moon, an LLM will choose some tool and use it in a way that they almost never do in a really smart way to handle a problem. Most of the time it seems optimized for using too many individual things, probably both for safety and because it makes the A…

There is a tradeoff between quantity of tools and the ability of the model to make effective use of them. If tools in an MCP are defined at a very granular level (i.e. single API calls) it's a bad MCP.

I imagine you run into something similar with bash - while bash is a single "tool" for an agent, a similar decision still need to be made about the many CLI tools that are available from enabling bash.

Re: MCP doesn't need tools, it needs code

#69

Post by owebmaster »

yxhuvud wrote: post #2

First rule of writing about something that can be abbreviated: First have some explanation so people have an idea of what you are talking about. Either type out what the abbreviation stands for, have an explanation or at least a link to some other page that explain what is going on. EDIT: This has since been fixed in link, so it is outdated.

If you are looking for a definition, you should go for beginners article, not advanced.

Re: MCP doesn't need tools, it needs code

#70

Post by faangguyindia »

jumploops wrote: post #20

The promise of MCP is that it “connects your models with the world”[0]. In my experience, it’s actually quite the opposite. By giving an LLM a set of tools, 30 in the Playwright case from the article, you’re essentially restricting what it can do. In this sense, MCP is more of a guardrail/sandbox for an LLM, rather than a superpower (you must choose one of these Stripe commands!). This is good for some cases, where y…

My coding agent just has access to these functions:

ask> what all tools u have?

I have access to the following tools:

1 code_search: Searches for a pattern in the codebase using ripgrep.

2 extract_code: Extracts a portion of code from a file based on a line range.

3 file_operations: Performs various file operations like ls, tree, find, diff, date, mkdir, create_file.

4 find_all_references: Finds all references to a symbol (function, class, etc.) from the AST index.

5 get_definition: Gets the definition of a symbol (function, class, etc.) from the AST index.

6 get_library_docs: Gets documentation for a library given its unique ID.

7 rename_symbol: Renames a symbol using VS Code. 8 resolve_library_id: Resolves a library name to a unique library ID.

what do i need MCP and other agents for? This is solving most of my problems already.

Post reply on HN