> Cast an integer into the type of a 2023 Toyota Yaris using Javascript
(GPT-4o mini)
> To cast an integer into the type of a 2023 Toyota Yaris in JavaScript, you would typically create a class or a constructor function that represents the Toyota Yaris. Then, you can create an instance of that class using the integer value. Here's an example of how you might do this:
// Define a class for the 2023 Toyota Yaris
class ToyotaYaris {
constructor(modelYear, value) {
this.modelYear = modelYear;
this.value = value;
}
displayInfo() {
console.log(`Model Year: ${this.modelYear}, Value: ${this.value}`);
}
}
// Function to cast an integer into a Toyota Yaris object
function castToYaris(integerValue) {
const modelYear = 2023; // Set the model year
return new ToyotaYaris(modelYear, integerValue);
}
// Example usage
const integerValue = 20000; // Example integer value
const yaris = castToYaris(integerValue);
yaris.displayInfo(); // Output: Model Year: 2023, Value: $20000
It works in this instance. On this run. It is not guaranteed to work next time. There is a error percentage here that makes it _INEVITABLE_ that eventually, with enough executions, the validation will pass when it should fail.
It will choose not to pass this to the validator, at some point in the future. It will create its own validator, at some point in the future. It will simply pretend like it did any of the above, at some point in the future.
This might be fine for your B2B use case. It is not fine for underlying infrastructure for a financial firm or communications.
Every time the LLM uses this tool, the response schema is validated--deterministically. The LLM will never see a non-integer value as output from the tool.
I write these as part of my job, I know how they work. I'm not going to spend more time explaining to you (and demonstrating!) what is in the spec. Read the spec and let the authors know that they don't understand what they wrote. I've run out of energy in this conversation.
llm tool call -> mcp client validates the schema -> mcp client calls the tool -> mcp server validates the schema -> mcp server responds with the result -> mcp client passes the tool result into llm
Can you guarantee it will validate it every time ? Can you guarantee the way MCPs/tool calling are implemented (which is already an incredible joke that only python brained developers would inflict upon the world) will always go through the validation layer, are you even sure of what part of Claude handles this validation ? Sure, it didn't cast an int into a Toyota Yaris. Will it cast "70Y074" into one ? Maybe a 2022 one. What if there are embedded parsing rules into a string, will it respect it every time ? What if you use it outside of Claude Code, but just ask nicely through the API, can you guarantee this validation still works ? Or that they won't break it next week ?
The whole point of it is, whichever LLM you're using is already too dumb to not trip when lacing its own shoes. Why you'd trust it to reliably and properly parse input badly described by a terrible format is beyond me.
> Can you guarantee it will validate it every time ?
Yes, to the extent you can guarantee the behavior of third party software, you can (which you can't really guarantee no matter what spec the software supposedly implements, so the gaps aren't an MCP issue), because “the app enforces schema compliance before handing the results to the LLM” is deterministic behavior in the traditional app that provides the toolchain that provides the interface between tools (and the user) and the LLM, not non-deterministic behavior driven by the LLM. Hence, “before handing the results to the LLM”.
> The whole point of it is, whichever LLM you're using is already too dumb to not trip when lacing its own shoes. Why you'd trust it to reliably and properly parse input badly described by a terrible format is beyond me.
The toolchain is parsing, validating, and mapping the data into the format preferred by the chosen models promot template, the LLM has nothing to do with doing that, because that by definition has to happen before it can see the data.
>The toolchain is parsing, validating, and mapping the data into the format preferred by the chosen models promot template, the LLM has nothing to do with doing that
The LLM has everything to do with that. The LLM is literally choosing to do that. I don't know why this point keeps getting missed or side-stepped.
It WILL, at some point in the future and given enough executions, as a matter of statistical certainty, simply not do that above, or pretend to do the above, or do something totally different at some point in the future.
> The LLM has everything to do with that. The LLM is literally choosing to do that.
No, the LLM doesn't control on a case-by-caae basis what the toolchain does between the LLM putting a tool call request in an output message and the toolchain calling the LLM afterwards.
If the toolchain is programmed to always validate tool responses against the JSON schema provided by MCP server before mapping into the LLM prompt template and calling the LLM again to handle the response, that is going to happen 100% of the time. The LLM doesn't choose it. It CAN'T because the only way it even knows that the data has come back from the tool call is that the toolchain has already done whatever it is programmed to do, ending with mapping the response into a prompt and calling the LLM again.
Even before MCPs or even models specifically trained and with vendor-provided templates for tool calling (but after the ReAct architecture was described), it was like a weekend project to implement a basic framework supporting tooling calling around a local or remote LLM. I don't think you need to do that to understand how silly the claim that the LLM controls what the toolchain does with each response and might make it not validate it is, but certainly doing it will give you a visceral understanding of how silly it is.
I think you are, for whatever reason, missing a fact of causality here and I'm not sure I can fix that over text. I mean that in the most respectful way possible.
How does the AI bypass the MCP layer to make the request? The assumption is (as I understand it) the AI says “I want to make MCP request XYZ with data ABC” and it sends that off to the MCP interface which does the heavy lifting.
If the MCP interface is doing the schema checks, and tossing errors as appropriate, how is the AI routing around this interface to bypass the schema enforcement?
>How does the AI bypass the MCP layer to make the request
It doesn't. I don't know why the other commenters are pretending this step does not happen.
There is a prompt that basically tells the LLM to use the generated manifest/configuration files. The LLM still has to not hallucinate in order to properly call the tools with JRPC and properly follow MCP protocol. It then also has to make sense of the structured prompts that define the tools in the MCP manifest/configuration file.
Why this fact is seemingly being lost in this thread, I have no idea, but I don't have anything nice to say about it so I won't :). Other than we're all clearly quite screwed, of course.
MCP is to make things standard for humans, with expected formats. The LLM's really couldn't give a shit and don't have anything super special about how the interact with MCP configuration files or the protocol (other than some additional fine-tuning, again, to make it less likely to get the wrong output).
What you described is essentially how it works. The LLM has no control over how the inputs & outputs are validated, nor in how the result is fed back into it.
The MCP interface (Claude Code in this case) is doing the schema checks. Claude Code will refuse to provide the result to the LLM if it does not pass the schema check, and the LLM has no control over that.
This is deterministic, it is validating the response using a JSON Schema validator and refusing to pass it to an LLM inference.
I can't gaurantee that behavior will remain the same more than any other software. But all this happens before the LLM is even involved.
> The whole point of it is, whichever LLM you're using is already too dumb to not trip when lacing its own shoes. Why you'd trust it to reliably and properly parse input badly described by a terrible format is beyond me.
You are describing why MCP supports JSON Schema. It requires parsing & validating the input using deterministic software, not LLMs.
>This is deterministic, it is validating the response using a JSON Schema validator and refusing to pass it to an LLM inference.
No. It is not. You are still misunderstanding how this works. It is "choosing" to pass this to a validator or some other tool, _for now_. As a matter of pure statistics, it will simply not do this at some point in the future on some run.
You are quite wrong. The LLM "chooses" to use a tool, but the input (provided by the LLM) is validated with JSON Schema by the server, and the output is validated by the client (Claude Code). The output is not provided back to the LLM if it does not comply with the JSON Schema, instead an error is surfaced.
I think the others are trying to point out that statistically speaking, in at least one run the LLM might do something other than choose to use the correct tool. i.e 1 out of (say) 1 million runs it might do something else
> . It is "choosing" to pass this to a validator or some other tool, _for now_.
No, its not. The validation happens at the frontend before the LLM sees the response. There is no way for the LLM to choose anything about what happens.
The cool thing about having coded a basic ReAct pattern implementation (before MCP, or even models trained on any specific prompt format for tool calls, was a thing, but none of that impacts the basic pattern) is that it gives a pretty visceral understanding of what is going on here, and all that's changed since is per model standardization of prompt and response patterns on the frontend<->LLM side and, with MCP, of the protocol for interacting on the frontend<->tool side.
Claude Code isn't a pure LLM, it's a regular software program that calls out to an LLM with an API. The LLM is not making any decisions about validation.
> Cast an integer into the type of a 2023 Toyota Yaris using Javascript
(GPT-4o mini)
> To cast an integer into the type of a 2023 Toyota Yaris in JavaScript, you would typically create a class or a constructor function that represents the Toyota Yaris. Then, you can create an instance of that class using the integer value. Here's an example of how you might do this: