News for hackers. Stuff that matters.

menix

Re:MCP Is Dead; Long Live MCP on Saturday March 14, 2026 @05:18PM (#47381282)
One aspect I think is often overlooked in the CLI vs. MCP debate: MCP's support for structured output and output schema (introduced in the 2025-06-18 spec). This is a genuinely underrated feature that has practical implications far beyond just "schema bloat."

Why? Because when you pair output schema with CodeAct agents (agents that reason and act by writing executable code rather than natural language, like smolagents by Hugging Face), you solve some of the most painful problems in agentic tool use:

1. Context window waste: Without output schema, agents have to call a tool, dump the raw output (often massive JSON blobs) into the context window, inspect it, and only then write code to handle it. That "print-and-inspect" pattern burns tokens and attention on data the agent shouldn't need to explore in the first place.

2. Roundtrip overhead: Writing large payloads back into tools has the same problem in reverse. Structured schemas on both input and output let the agent plan a precise, single-step program instead of fumbling through multiple exploratory turns.

There's a blog post on Hugging Face that demonstrates this concretely using smolagents: https://huggingface.co/blog/llchahn/ai-agents-output-schema

And the industry is clearly converging on this pattern. Cloudflare built their "Code Mode" around the same idea (https://blog.cloudflare.com/code-mode/), converting MCP tools into a TypeScript API and having the LLM write code against it rather than calling tools directly. Their core finding: LLMs are better at writing code to call MCP than at calling MCP directly. Anthropic followed with "Programmatic tool calling" (https://www.anthropic.com/engineering/code-execution-with-mc..., https://platform.claude.com/docs/en/agents-and-tools/tool-us...), where Claude writes Python code that calls tools inside a code execution container. Tool results from programmatic calls are not added to Claude's context window, only the final code output is. They report up to 98.7% token savings in some workflows.

So the point here is: MCP isn't just valuable for the centralization, auth, and telemetry story the author laid out (which I fully agree with). The protocol itself, specifically its structured schema capabilities, directly enables more efficient and reliable agentic workflows. That's a concrete technical advantage that CLIs simply don't offer, and it's one more reason MCP will stick around.

Long live MCP indeed.

Re:Claude Advanced Tool Use on Monday November 24, 2025 @04:43PM (#46039738)
smolagents by Hugging Face tackles your issues with MCP tools. They added support for the output schema and structured output provided by the latest MCP spec. This way print and inspect is no longer necessary. https://huggingface.co/blog/llchahn/ai-agents-output-schema
Re:Claude Advanced Tool Use on Monday November 24, 2025 @04:04PM (#46039294)
The latest MCP specifications (2025-06-18+) introduced crucial enhancements like support for Structured Content and the Output Schema.

Smolagents makes use of this and handles tool output as objects (e.g. dict). Is this what you are thinking about?

Details in a blog post here: https://huggingface.co/blog/llchahn/ai-agents-output-schema

Re:Claude Advanced Tool Use on Monday November 24, 2025 @04:01PM (#46039265)
Wrapping tool calls in code together with using the benefits of the MCP output schema was implemented in smolagents for some time. Think that’s even one step further conceptually. https://huggingface.co/blog/llchahn/ai-agents-output-schema
Re:Code Mode: the better way to use MCP on Saturday September 27, 2025 @05:23PM (#45399426)
smolagents provides something very similar: https://huggingface.co/blog/llchahn/ai-agents-output-schema
The latest Model Context Protocol introduces Output Schema: agents now know the exact data structure a tool will return before calling it.

This eliminates the "print-and-inspect" pattern where CodeAct agents call tools just to discover what data they get back. Instead of multi-step exploration, agents can write complete, precise programs from the start.

What's new: Tools declare their output schemas upfront

What's better: Agents plan complete execution paths instead of reactive discovery

Now supported in Hugging Face smolagents.

Re:Ask HN: Migraine prophylaxis? on Tuesday July 24, 2018 @06:08AM (#17599563)
For me magnesium (oral) works very well. 100mg to 300mg per day. Decreased my migraine from weekly to once per half year.
Re:Update on the Swift Project Lead on Tuesday January 10, 2017 @01:08PM (#13367189)
Mark Gurman even mentioned a lot of good people were leaving the company. (https://www.bloomberg.com/news/articles/2016-12-20/how-apple...)