Agent Protocols news and analysis on Web Pulse: 3161 curated articles tracking the latest Agent Protocols developments, tools, and research, updated continuously from vetted sources.
WordPress.com opened its Model Context Protocol (MCP) agent integration to free-plan sites through November 2026, letting users connect AI agents such as ChatGPT or Claude to manage their sites through conversation, acco…
Bravo 01 Labs & Dynamics has opened early-access registration for Cubo, an AI-native search engine with MCP integration and a Search API priced at $5 per 1,000 searches at launch, rising to a standard price of $6 per 1,0…
An open-source Android agent called Mika, published at github.com/wangzan101/Mika under the Apache-2.0 license, reached about 1,682 GitHub stars and release v0.1.16 by October 31, 2026, two days after the repository was …
The lspkit project released a Rust framework that serves one code-analysis engine over both the Language Server Protocol for editors like VS Code and the Model Context Protocol for AI coding agents including Claude Code,…
Arcjet cited a September study by an independent researcher that captured 37 requests from ten AI assistants to a Cloudflare Worker, using the researcher's DuckAssistBot capture alongside SeatGeek's ChatGPT example in it…
Zed Industries published the Agent Client Protocol (ACP) on August 27, 2025, in partnership with Google, with Gemini CLI as the reference implementation, to let any coding agent work inside any code editor without a besp…
SpyCloud reported on October 30 that infostealer logs from the WardenStealer and Aoki malware families contain credentials for local AI coding tools, including Claude Code OAuth access and refresh tokens, tokens for conn…
Recall Kitchen's MCP server now lets AI agents pay per call for recall lookups using x402, charging $0.025 in USDC on Base once an anonymous IP quota of 5 searches per hour and 15 per day is exhausted, with photo search …
A developer launched Kuzmich, a free AI travel guide on the Vedar portal for Kamchatka that aggregates 78 tours from local operators into a single catalogue, with requests routed directly to operators. The site also offe…
Roblox reported on October 29 that daily users of its MCP server grew nearly 5x since Q2, as creators adopted external AI coding tools on the platform, and that time spent with AI tools tripled among top creators. Roblox…
A developer outlined a design for a read-only marketing reporting agent built on either OpenAI Custom GPTs or Claude, using Actions and MCP connectors respectively to pull Ads, Analytics and CRM data. The approach constr…
A new open-source browser extension called Web MCP Bridge lets ChatGPT, Gemini and Claude web interfaces call local Model Context Protocol (MCP) servers without API keys or paid subscriptions, routing tool requests throu…
OpenAI, Google, Microsoft and Anthropic all committed on Friday to honouring a single new robots.txt policy token, `__usage_ai-training`, that lets site owners opt out of AI training without blocking each company's crawl…
A developer built locli, an open-source CLI and MCP server that lets coding agents like Claude Code, Cursor and Codex localize apps end to end — consolidating duplicate string keys across iOS, Android, web and backend in…
OpenTelemetry shipped semantic conventions release v1.42.0 on June 12, 2026, deprecating every gen_ai.* attribute, span, metric, and event in its core repository and moving them to a dedicated semantic-conventions-genai …
Sourcemeta has released tooling that automatically upgrades any JSON Schema to the dialect a given tool expects, via the JSON Schema CLI or the Sourcemeta One registry, addressing fragmentation across the standard's many…
OpenAI, Google, Microsoft and Anthropic will adopt a shared "policy token" signal in robots.txt that lets publishers apply AI training opt-out preferences across multiple AI companies instead of setting them individually…
The Qwen Code project has built a terminal-based AI coding agent that switches between OpenAI, Anthropic, Gemini, Qwen APIs and local models such as Ollama and vLLM at runtime without rewriting tool definitions or restar…
AgentDAST has launched as a website security API that lets AI agents run bounded, read-only checks on owned websites for exposed files and secrets, with access through REST or MCP. Before any assessment starts, the owner…
CrowdStrike introduced Agent Graph, a relational layer beneath its Falcon Guardian product that links AI agent prompts, models, tools, skills, MCP servers, processes, files and detections into a single causal chain runni…