Everything you need to integrate with the Remote API
In-depth articles and integration guides
Curious about where your Model Context Protocol (MCP) server should live—on your machine or in the cloud? This article breaks down the core differences between local and remote MCP setups, including speed, privacy, ease of use, and scalability. Whether you're a developer building new AI tools or deploying services for end users, this guide will help you choose the right MCP setup for your use case.
OAuth 2.0 was designed for clients known at build time. As AI agents make runtime decisions, delegate to sub-agents, and traverse trust boundaries, the cracks are showing. A practical breakdown of MCP OAuth 2.1, A2A, AAuth, WIMSE, and what a production-grade agent auth architecture looks like today.
TL;DR: MCP tool definitions can burn 55,000+ tokens before an agent processes a single user message. We built the Apideck CLI as an AI-agent interface instead:an ~80-token agent prompt replaces tens of thousands of tokens of schema, with progressive disclosure via `--help` and structural safety baked into the binary. Any agent that can run shell commands can use it. No protocol support required.
For 15 years, developer experience meant optimizing for humans at a terminal. That model is increasingly incomplete. A growing share of API traffic is generated by AI agents that read docs, make decisions, and retry failures autonomously. This is the same discipline as DX applied to a new consumer. Call it agent experience, or AX.
In this article, we dive deep into what MCP actually is, how it works behind the scenes, and why it’s being called the “USB-C for AI models.” You’ll explore how it simplifies AI integrations, the roles of Hosts, Clients, and Servers, and the security risks developers need to keep in mind.
This article dives deep into the current state of MCP security in 2025, covering real-world vulnerabilities like prompt injection, tool poisoning, and token exposure. You’ll learn about the biggest threats facing MCP implementations today, including exploits seen in GitHub, Supabase, and others—plus what the new OAuth 2.0-based security spec is doing to address them.
On the first of February 2021, I started as a Frontend Engineer at Apideck, a remote role at a fast-growing startup that helps SaaS companies build & scale API-driven platforms. In this post, I’m going to talk about how I ended up at this company, why it’s so exciting and how I experienced my first month.
Get updates about your favorite APIs and SDKs.
Subscribe for the beta