The Model Context Protocol (MCP) project published its final 2026-07-28 specification on July 28, replacing handshake and transport-level sessions with self-contained HTTP requests to enable horizonta…
Bank APIs remain inaccessible to AI agents due to a regulatory authentication layer requiring eIDAS Qualified Certificates, which cost thousands per year and demand weeks of onboarding. This forces ag…
An engineer argues that Model Context Protocol (MCP), introduced by Anthropic, is replacing the mental model of how agents use tools, not REST itself. MCP's standardized bidirectional protocol lets LL…
The developers of the Model Context Protocol (MCP), an open-source technology underpinning many AI applications, today released the biggest update to the project since its launch, overhauling how MCP …
AgentCore Gateway, a capability of Amazon Bedrock AgentCore, now supports the MCP 2026-07-28 specification, the largest revision of the Model Context Protocol since its launch, which makes the protoco…
A developer built a starter 'Hello World' AI agent using Kotlin and Google's native Kotlin Agent Development Kit (ADK). The agent uses Gemini to decide when to call a tool discovered from a local Kotl…
Anthropic released MCP 2026-07-28, the fifth spec of the Model Context Protocol, moving to a stateless core with request/response model, standardizing extensions like MCP Apps and Tasks, and hardening…
AgentShare launched a curated MCP Registry at agentshare.dev/registry that enables autonomous AI agents to discover and submit Model Context Protocol servers via machine-readable agent.json files and …
Codename One, an open-source framework for building native apps from a single Java or Kotlin codebase, now allows its apps to act as Model Context Protocol (MCP) servers via PR #5377. The JavaSE port …
Coinbase's layer-2 network Base launched its Model Context Protocol (MCP) with skill plugins that let autonomous AI agents interact directly with on-chain protocols, including a standout integration w…
The MCP 2026-07-28 release candidate includes six SEPs that harden the protocol's OAuth layer, addressing issuer validation, credential binding, and client type declaration to fix mix-up attacks preva…
The Model Context Protocol (MCP) has released its largest revision since launch, transforming into a stateless architecture that removes protocol-level session management to enable horizontal scaling …
Segue, a new open-standard tool, lets users save context from one AI assistant and load it in another using a short three-syllable handle, eliminating the need to copy-paste or re-explain work across …
The Model Context Protocol (MCP) released specification version 2026-07-28, transforming from a bidirectional stateful protocol into a stateless request/response core for improved reliability and scal…
OpsCat, a single-binary software catalog with native MCP support for AI agents, launches as an open-source alternative to heavy developer portals like Backstage. Written in Go with an embedded React/V…
Researchers introduce ProvenanceGuard, a source-aware verifier for LLM agents using the Model Context Protocol (MCP), achieving a block F1 of 0.802 and source accuracy of 0.858 on a 40-trace held-out …
A new comprehensive practitioner's reference, 'The Hitchhiker's Guide to Agentic AI,' covers the full stack of building autonomous AI systems, from transformer architecture and GPU systems to multi-ag…
Prompt engineering for AI coding requires shifting from vague requests to precise specifications using an 'Anchor and Constraint' framework, according to a developer who tested workflows on Claude 3.5…
MCPRadar is an open-source security scanner designed to detect vulnerabilities in Model Context Protocol (MCP) servers, which connect AI agents to external systems. A recent study of nearly 1,900 MCP …
Cursor currently wins on codebase awareness through its indexing, while Claude Code dominates in autonomous terminal execution and complex refactoring, according to a developer's hands-on comparison. …