Find a story
Search Spins
Search titles, summaries, and missing voices across published articles — press releases, announcements, and media coverage.
13 results for “Model Context Protocol”
Marimo Notebook Flaw Could Run MCP Commands Before Cells Execute in Edit Mode
A high-severity security vulnerability in Marimo Notebook allowed arbitrary Model Context Protocol (MCP) commands to execute as local subprocesses upon opening a malicious notebook in edit mode, before cell execution — now patched.
Aug 25, 2026
Cloudflare WriteGuard Brings Fine-Grained Security Controls for MCP Servers
Cloudflare launched WriteGuard, a private-beta security tool for MCP servers, designed to restrict AI agents' ability to modify data or perform actions—extending beyond read-only access controls.
Aug 18, 2026
How MCP Servers Can Expose Enterprise Secrets
The article identifies security risks in Model Context Protocol (MCP) servers — specifically plaintext config exposure, over-permissioned access, and prompt injection — that may go undetected by enterprise security teams as AI agents are integrated.
Aug 17, 2026
CloudFlare Previews Automatic WebMCP Support for Web Pages
Cloudflare introduced a developer preview enabling websites to expose a WebMCP interface via a single dashboard toggle, allowing AI agents to interact with web pages through structured protocols rather than unstructured scraping.
Aug 11, 2026
Webull expands AI-powered investing ecosystem
Webull expanded its AI-powered investing tools by integrating third-party LLMs and launching developer-facing interfaces, positioning itself as a platform enabling AI-augmented trading workflows.
Aug 4, 2026
Dropbox Integrates MCP and Dash to Close the Gap Between Security Design and Code Review
Dropbox integrated Model Context Protocol (MCP) with its internal Dash knowledge platform to inject security design context—such as threat models and requirements—into AI-assisted code reviews, aiming to align implementation with security intent.
Jul 31, 2026
Article: Securing MCP in Production: Defense-in-Depth Beyond the Gateway
The article introduces a four-layer defense-in-depth architecture for securing Model Context Protocol (MCP) deployments in production, emphasizing security enforcement beyond the gateway at earlier control points.
Jul 29, 2026
The Agentic AI Foundation updates MCP with a fully stateless architecture, a hardened authentication model, a formal 12-month deprecation policy, and more (Michael Nuñez/VentureBeat)
The Agentic AI Foundation released an update to the Model Context Protocol (MCP), introducing architectural, security, and governance changes including statelessness, hardened authentication, and a formal deprecation policy.
Jul 29, 2026
MCP’s biggest update removes the machinery many servers were built around
The Model Context Protocol (MCP) is removing session state, initialization handshakes, and capability negotiation from its core specification to simplify remote server deployment and align with stateless HTTP infrastructure patterns.
Jul 26, 2026
Model Context Protocol is going stateless to make scaling simpler - InfoWorld
The Model Context Protocol (MCP) is transitioning to a stateless architecture to improve scalability, though the article provides no technical details, implementation timeline, or evidence of current scaling bottlenecks.
Published Jul 24, 2026 · Analyzed Jul 27, 2026
Model Context Protocol prepares to break with its stateful past - The Register
The Model Context Protocol (MCP) is transitioning from a stateful architecture to a stateless design, aiming to improve interoperability and reduce implementation complexity for AI tool integrations.
Jul 24, 2026
HeirWealth switches on MCP server
HeirWealth launched an MCP server integrated into its wealth management platform to enable plain-language AI querying of consolidated client financial data by financial professionals.
Jul 10, 2026
AI Model Context Protocol Adds Centralised Auth for Enterprise
The Model Context Protocol (MCP) team has released the Enterprise-Managed Authorisation extension as stable, enabling organisations to centrally manage user access to MCP servers via their existing identity providers.
Published Jul 6, 2026 · Analyzed Jul 8, 2026