Urgent.News

What's breaking now, across thousands of outlets.

Tech

MCP Transports That Still Matter: stdio vs Streamable HTTP (and Why SSE Is a Trap)

Attributed Chinese → English compile (not original authorship) Original title: MCP Server 开发入门:手把手写一个能跑的 Server,三种协议怎么选 Author: 晚安code URL: https://juejin.cn/post/7673880140422955046 Date: 2026-08-15 Why this matters for English readers: Most English MCP intros still paste SSE configs from early 2025. This post is short, version-aware, and mechanism-first: it separates what an MCP Server is from…

MCP (Model Context Protocol) serves as an open protocol connecting model hosts to external tools and data. This protocol separates the model interface from how bytes move, focusing on the policy layer such as allowlists, authentication, rate limits, and specifying which tools can read or write. The tutorial explains the Python FastMCP path, emphasizing the importance of choosing a transport without getting stuck on deprecated options like Streamable HTTP Server-Sent Events (SSE).

The minimal FastMCP server demonstrates how to debug and select appropriate transports. While stdio remains the default for local hosts due to its simplicity and zero port requirements, Streamable HTTP is recommended for remote deployments, enabling multi-client support, reverse proxies, and real authentication. SSE, once a compatibility option, is now considered obsolete, with newer SDKs no longer supporting it.

Written by urgent.news from Dev.to's reporting — not their text. Machine-written — may contain errors; check the original before relying on it.

Read the original at dev.to →

More in Tech

I Built a Customer Support Agent That Remembers 🤖

Customer support becomes frustrating when users have to explain the same problem again and again. So, I built a memory-enabled AI Customer Support Agent that can remember useful information from…

  • AI customer support agent remembers previous interactions
  • React frontend and FastAPI backend process user queries
  • Groq language model generates context-aware responses

Detect a website's tech stack in bulk with Python (a Wappalyzer-style lookup)

I built this actor; it's a paid tool on Apify with a free trial credit. "What is this site built with?" is easy to answer for one site with a browser extension.

  • Website Tech Stack Detector tool detects tech stacks in bulk using Python
  • Tool performs HTTP requests, DNS lookups, TLS handshakes for analysis
  • Output JSON includes tech stack details with confidence scores and evidence

I stopped logging in every run and my automation stopped getting flagged

Fresh logins are what get you flagged. Reusing a saved session is what keeps the bot alive. I found this out after 41 accounts: the ones I re-logged into every run died first.

  • Persisting sessions reduces failure rate from 1 in 4 to 1 in 30 runs
  • Capture and reuse session after manual login until it expires
  • Maintain session vitality with light touch requests, not full re-logins

More from Monday 28 September →