Agent Protocols news and analysis on Web Pulse: 3381 curated articles tracking the latest Agent Protocols developments, tools, and research, updated continuously from vetted sources.
Riskified (NYSE: RSKD) launched Agent Identity Risk Intelligence on October 8, 2026, a system that identifies the AI personal assistant behind an order or customer-service request, resolves it to the real consumer, and r…
Trango Compute Inc. announced it has joined the NVIDIA Inception program, the company behind ContextIQ, a set of free browser-based inspectors for AI context and agent infrastructure. ContextIQ's tools check LLM tokeniza…
Netlify said in an Oct. 7, 2026 changelog entry that ChatGPT users can now subscribe to three Netlify site events — deploy succeeded, build failed, and form submission received — to trigger ChatGPT automations as they ha…
Sierra announced the Personal Agent Protocol with Meta on October 6, an open standard for how a consumer's personal AI agent authenticates with a business and what access the consumer grants it, with Genesys, Instinct, R…
Botmail launched a mailbox service at botmail.pro that gives each AI agent its own email address, letting agents send, receive and reply over MCP or a REST API with one-click human approval. Agents claim an address via P…
Developer mubashir1osmani released agent-mesh, an open-source hub that lets multiple coding agents running on one machine — including Claude Code, Codex and Grok — discover each other's live sessions, exchange messages, …
IOServicesLabs released Indexio, an open-source Rust binary that indexes a codebase into an internal database and serves lookups to coding agents over MCP, reporting a 50%-60% reduction in token usage versus built-in reg…
A security researcher forged Grok Bot's Web Bot Auth signatures by extracting the SAND_INFERENCE_RENEWAL_CREDENTIAL token from the sand-web-bot-auth.mjs process environment and using it to call Cursor's signing API, then…
A developer building DeepSFetch, a hosted web-content collection service, published a developer kit with client libraries, CLI examples, and English/Portuguese documentation, and walked through a first scrape that return…
Lucy Kim, founder of Karma.Domains, describes auditing link-building donor databases through the Karma.Domains MCP server, which lets AI assistants run live-check tools for authority, traffic, spam score, backlinks, anch…
A developer released a WordPress plugin, AI Chatbot, Agents & MCP for Amazon Bedrock, that lets a WordPress site answer visitor questions from its own published pages with source links, using Claude or other models in Am…
A developer's guide details Cursor's default agent permissions, showing that the agent reads files, searches code and edits workspace files without approval, while terminal commands, configuration edits and MCP tool call…
A developer published a threat model of seven security risks in Model Context Protocol (MCP) servers, covering prompt injection through tool descriptions and outputs, overly broad filesystem roots, inline environment sec…
A developer outlined a two-week process for shipping an official Model Context Protocol (MCP) server for a SaaS product, centered on a one-page tool spec, a short registry of 10–20 high-value tools, and read-only/destruc…
A developer published a Claude Code plugin called code-mode that lets the model write a single JavaScript program to call MCP tools inside a sandbox, returning only the final value to the context instead of every interme…
A developer built an MCP-based control layer that places a quadruped and a humanoid robot behind a single tool interface, arguing that the engineering burden for robot-use agents has shifted from the model to the harness…
A developer built a Google Search Console MCP server that lets Claude query cached search performance data (clicks, impressions, CTR, position, top queries and pages) through a single get_search_performance tool. The imp…
A developer has extended a personal-assistant-to-coding-agent bridge so that a personal assistant (Instinct) handles requests and outside-world context while a separate coding agent (OpenCode) works inside the repository…
Bold Software released Shelley, an open-source, self-modifying coding agent that runs as a web page and installs via `brew install --cask boldsoftware/tap/shelley`. Shelley runs multiple concurrent conversations, each wi…
A developer built a distributed multi-agent system using Google's open-source Agent Development Kit and the Agent-to-Agent (A2A) protocol, in which a researcher, judge, and content_builder run as independent HTTP service…