GitHub MCP Server now supports the next MCP specification ahead of its official release on 28th July 2026, which transitions the protocol to a stateless core for easier scaling. The server removed Red…
Andrew Ng released OpenWorker, an open-source desktop AI agent that produces finished deliverables instead of chat, running entirely on the user's machine. The four-layer architecture includes a Tauri…
The U.S. Food and Drug Administration (FDA) has built ELSA, a generative AI platform available to all 16,000 staff, and Halo, a governed data foundation on Databricks, achieving 85% daily staff adopti…
Bright Security published research on ANSI escape sequence injection in MCP servers, an attack class that exploits the gap between what a terminal renders and what an AI agent reads. The attack can hi…
Hedgy released Setoku, a self-hosted knowledge server for AI agents that uses a ClickHouse data lake and MCP protocol to let Claude-powered agents store and query company knowledge, with no inference …
A developer proposes an agentic validation and inspection layer built with LangGraph, MCP, and A2A to complement traditional CI/CD pipelines. The architecture combines deterministic tools like SQL lin…
The release candidate for the next Model Context Protocol specification, locked on May 21, 2026, with the final spec scheduled for July 28, 2026, delivers a stateless protocol core, an Extensions fram…
Temrel released mcp-spec-audit, a static analysis tool that scans MCP server codebases for breaking, deprecated, and advisory changes ahead of the MCP 2026-07-28 spec revision, which reshapes the prot…
Anthropic's Model Context Protocol (MCP) is finalizing its specification on July 28, dropping the initialize handshake and session IDs to eliminate sticky routing and shared state stores, making MCP b…
Infrastructure developer Earendil Works gave its Pi coding agent a single tool called fabric_exec, which accepts TypeScript programs that call Pi's capabilities as an API, and one such program ran con…
Traceforce has launched an AI security monitoring tool that maps connectivity between AI apps, MCPs, and triggered tools to address shadow AI sprawl in workplaces. The system deploys a Go-based binary…
A developer built SymbolPeek, an MCP server that gives AI coding agents symbol-level access to a codebase, reducing context consumption by over 95%. In real-world testing, the tool avoided reading 6.4…
A developer discovered that while their requirements.txt pins the MCP library version, the actual contract their MCP server exposes to agents—tool names, parameter shapes, and descriptions—is generate…
A developer released Fitter, an open-source scraping engine that converts any website or API into structured JSON using declarative YAML/JSON configs instead of code, enabling LLMs like Claude Code to…
A new spec, Overview Usage Analytics, defines a contract for tracking skill usage in a SQLite invocation ledger alongside existing MCP server analytics, requiring the home overview card to render rank…
InsForge CEO Hang Huang compares his company's AI-native backend platform with Supabase, arguing that InsForge is designed for agentic coding where AI agents provision and operate the backend automati…
A gateway enforces policy on calls passing through it, but governance answers deeper questions about entitlement, approval, scope, duration, and revocation, according to C1 Field CISO Kevin Paige and …
Agents should write code instead of calling many custom tools, argues Browserbase. A single code-execution surface reduces context usage by roughly 88% compared to 40 always-loaded tools, because mode…
A technical walkthrough of Model Context Protocol (MCP) tool calling reveals that when an AI agent appears to create a Jira ticket, the model actually generates a structured request for the applicatio…
SUUR Things has released an open-source MCP server and local dashboard for Things 3 on macOS that gives AI agents like Claude read-only access to the Things SQLite database and write access only throu…