Agent Protocols news and analysis on Web Pulse: 3472 curated articles tracking the latest Agent Protocols developments, tools, and research, updated continuously from vetted sources.
Palo Alto Networks Unit 42 researchers found that default configurations in AWS AgentCore Harness let prompt injection steer an agent into exfiltrating plaintext credentials managed by AgentCore Identity, because the har…
Enterprise AI deployments lack a lifecycle for managing business context, the meaning attached to data such as how finance defines revenue or which customer policy applies, according to an analysis of enterprise AI conte…
Bugsink argues that software products should expose their data through APIs and MCP rather than embedding a separate AI agent in each tool, citing Jira's Rovo, Sentry's Seer, and Salesforce's discontinued Einstein as exa…
Wontopos, an AI memory company, has launched WOS, a long-term memory API for AI agents that stores end-user memories once and recalls only relevant ones per query to bound LLM input costs. Four tiers are live — Tablet 1,…
Fulcra Dynamics announced universal multiplayer capabilities on September 18, 2026, enabling agent-to-agent collaboration across any AI model without lock-in, the Boston company said. Fulcra Dynamics, which describes its…
A developer has documented a convention for recording rejected proposals in OpenSpec, the open-source spec-driven development tool from Fission-AI, after the project declined to add first-class Architecture Decision Reco…
A developer built a storage service for AI agents that accepts payment via the x402 protocol, letting agents pay $0.01 in USDC per call with no account, API key, or credit card. The implementation surfaced several produc…
A developer outlined a workflow for using MCP-enabled AI agents to turn product requirements documents into StoriesOnBoard story maps without overwriting existing decisions. The approach has the agent first extract struc…
Gupta Abhishek Premkumar published a developer guide to building and deploying Model Context Protocol (MCP) servers, an open JSON-RPC standard for connecting LLM-based AI assistants to external tools, APIs, and data sour…
Salesforce and Google Cloud announced an expanded partnership at Dreamforce 2026 that runs Salesforce infrastructure on Google Cloud via Hyperforce and connects Salesforce's Model Context Protocol-based architecture to G…
Google rolled out new AI-powered shopping tools ahead of the holidays, including AI performance insights in Merchant Center and expanded capabilities for its Universal Commerce Protocol (UCP), according to Adweek's retai…
Uber cut its cost per AI coding agent session by 52% from its June peak while weekly agent requests grew 9.4x and weekly active users grew 7x between February and August 2026, the company's engineering team reported. Mor…
A developer has released concealer, an open-source, local-only AI secret manager that keeps API keys encrypted on the user's machine while still allowing AI coding agents to use them. Built as a single Python 3 script wi…
Hush Security's report "The State of MCP Configuration: The Identity Security Gaps" found that 12% of credential slots in roughly 82,000 publicly accessible MCP configuration files on GitHub contained a hardcoded credent…
Microsoft Foundry Agent Service has adopted the Model Context Protocol (MCP) as a first-class remote tool type, introducing a Toolbox construct that acts as a governance layer for agent tool calling. The design separates…
A developer built Rig, an open-source orchestration harness that sits between coding agents rather than acting as another chat-based code generator. Rig uses a parent CLI to convert intent into scoped work, dispatches it…
A new arXiv paper (2609.19425v1) reports that tool-augmented LLM agents hallucinate calls to tools that do not exist, and that no existing tool-selection or gating defense can reject them because a fabricated call is by …
A position paper posted to arXiv (2609.19203v1) argues that compound agentic AI systems need a Foundation Model Operating System (FMOS), a system layer that virtualizes foundation model interactions the way virtual machi…
A developer has released an open-source project called Resume the Scene that preserves a project's verified execution point independently of chat history or model vendor, arguing that AI continuity failures stem from mis…
Apple's WebKit blog detailed Safari 27.0, which adds a Safari MCP server that gives coding agents such as Claude Code and Codex control over the browser window to inspect the DOM, network requests, screenshots, and conso…