openapi

A developer argues that MCP (Model Context Protocol) repeats the same design flaws as GraphQL — being verbose, hard to cache, insecure, and reinventing existing web standards poorly — and warns it will cost users in tokens and money due to inefficient implementations.

Sierra's Personal Agent Protocol publishes its first draft (0.1), detailing direct sign-in flows and a /.well-known/poppy.json discovery spec for builders, alongside 35 new design partners including Meta, Shopify, Stripe, and Walmart.

Built riviera.so, a tool that lets developers edit the tool and parameter descriptions that AI agents read via OpenAPI or MCP servers, without redeploying the backend. It supports draft/publish versioning, failure investigation, and turning agent mistakes into tool-selection tests.

A developer's blog rant about common API design frustrations encountered while automating Vori's onboarding flow, including gated documentation, missing OpenAPI specs, lack of self-serve credential issuance, and poor credential identity handling.

Earendil explains why Pi reversed its earlier 'no MCP' stance and brought Model Context Protocol support into the core, arguing modern MCP plus Codemode-style JavaScript sandboxing solves longstanding tool composition problems. The post also details how the changes improve tool metadata, deferred tool loading, and Jev integration.

The author is building a software generation platform and questions whether it should know about generated components, advocating for artifact-based contracts and lifecycle management.

Octri.dev launches on Product Hunt, letting developers upload an OpenAPI spec to auto-generate customizable docs, client SDKs in ten languages, and an MCP server so AI agents can call their APIs — with built-in production error reporting and GitHub sync.

Cadenya is a hosted agentic loop service that enables running AI agents with tool integration via OpenAPI and MCP, handling context compaction, approvals, and other features.

A discussion on whether the Model Context Protocol (MCP) remains relevant as AI agents increasingly crawl websites or Swagger/OpenAPI docs directly, comparing the reliability and advantages of each approach.

mcpgen is a CLI tool that turns any OpenAPI 3.x spec or Postman collection into a fully functional, self-contained Python MCP server with auto-detected authentication, no runtime dependency, and generates deployable source code.

A developer tool that converts OpenAPI V3 specifications (from URL or file) into AI agent skill markdown files, enabling efficient API interaction with reduced token usage.

A README for the RedHatInsights/javascript-clients monorepo that auto-generates Javascript API clients for Swagger/OpenAPI specs, using NX for monorepo management and GitHub Actions for CI/CD and NPM publishing.

AgentLighthouse is a local-first tool that scans repositories, docs, and APIs to assess how well AI coding agents (like Codex, Claude Code, Cursor) can understand and use a project. It checks for agent instruction files, documentation quality, setup clarity, OpenAPI operation quality, MCP tool descriptions, and more.