Agent Protocols news and analysis on Web Pulse: 3388 curated articles tracking the latest Agent Protocols developments, tools, and research, updated continuously from vetted sources.
Shopify has added Google's Gemini app to its Agentic Storefronts initiative, letting eligible US merchants surface catalog products inside Gemini and Google AI Mode conversations. For those stores, Shopify-powered direct…
Nimbalyst released a free, MIT-licensed Wiki plugin for OpenAI's Codex that lets the coding agent write plain markdown project pages — a Home page, decisions and their rationale, open questions with owners, and tracking …
Wren AI released a Claude integration that lets the model build an executive dashboard from a single prompt, translating one request into 24 governed queries across 20+ databases through a single MCP connection. The Wren…
A developer tested RollingGo's hotel MCP server on ModelScope, which offers free, unlimited-call access to hotel search, room detail, and price confirmation data covering 2M+ properties and 110K+ direct-contracted hotels…
Sierra published a draft of the Personal Agent Protocol, called Poppy, and added 35 design partners including OpenAI, Visa, Mastercard, PayPal, Bank of America, Target, Shopify and Stripe, following its Tuesday announcem…
Registrum launched a hosted Model Context Protocol endpoint that serves live UK Companies House data, including company search, officer records, filings, and ownership chains traced to beneficial owners, without requirin…
Developer Nemanja Milosevic open sourced Integrum, an MIT-licensed library that generates MCP servers from existing Python modules, libraries, or plain classes, under the AlphaDeep project. Integrum uses an in-memory obj…
A second-generation Spanish family business servicing and repairing car-wash equipment has built its own ERP in production and a set of AI agents on Claude Code and an MCP server, despite having no programmers on staff. …
A developer building Mac MCP, an open-source local control layer that lets MCP-compatible AI clients drive Safari, Chrome, files and native macOS apps, describes the concurrency problems that surface when two AI agents s…
A developer published an MCP browser extension, `@mehmoodqureshi/chrome-mcp`, that connects a local Model Context Protocol server to the Chrome profile a user is already signed into, letting an AI agent drive real tabs w…
A developer published a walkthrough for building a secure remote Model Context Protocol server in ASP.NET Core using the official MCP C# SDK 2.2 on .NET 10, wrapping the stateless 2026-07-28 spec with API-key authenticat…
A developer behind the MCP security scanner WARDEN benchmarked it against two open-source scanners, mcp-audit and mcp-shield, on 485 poisoned tool definitions extracted from the MCPTox dataset and on 986 public servers f…
A developer built nittim, an auditor that scans AI-written applications for committed secrets, vulnerable dependencies, broken authorization, GitHub Actions script injection, and leaked client-side data. Running full aud…
OpenAI's plugin developer portal is triggering a "Complete identity verification" dialog for some macOS users on Chrome and Safari when they try to create a plugin via the "With MCP" path at platform.openai.com/plugins, …
OpenAI's plugin creation flow at platform.openai.com/plugins is stuck in an identity verification loop that blocks developers from starting new "With MCP" plugin projects even when their organization settings show a veri…
Senro launched as a WebMCP evaluation and observability tool that tests a website's WebMCP tools and monitors how AI agents use them in production, according to the company's Show HN post. Senro says it provides this rel…
APIblaze launched in beta as a serverless MCP and API gateway that enforces authorization policies at the gateway, hosts the MCP server, OAuth discovery and login pages, and forwards requests to backends running on local…
A developer built Oraviz-MCP, a minimal, read-only Model Context Protocol server for Oracle AI Database that exposes seven tools for running queries, profiling tables and generating charts, as a proof of concept for lett…
Oracle released Oracle AI Agent Memory 26.8 on 22 September, adding integration with Oracle Deep Data Security so the database itself enforces which signed-in user can read or write each agent memory record. The release …
A developer published a practical security checklist for MCP servers, arguing that because tools touch filesystems, databases, package managers and deployment APIs, the server itself becomes the authorization boundary. T…