Loading story…
The Model Context Protocol (MCP) is undergoing a wire-level redesign that replaces session-based connections and initialization handshakes with a stateless, request-centric model aimed at simplifying deployment and horizontal scaling. Under the release candidate, protocol version, client capabilities, and client identity move into per-request metadata, while routable transport headers, deterministic caching behavior, and a new server/discover method are intended to make remote MCP servers easier to run behind standard cloud load balancers without session affinity, shared session stores, or MCP-specific routing logic.
The update also adds Multi Round-Trip Requests, interactive MCP Apps, and an authorization framework built on OAuth 2.1 and OpenID Connect, while deprecating legacy features including Sampling, Roots, Logging, the older HTTP+SSE transport, Dynamic Client Registration, Tasks, and some server-initiated request patterns. Developers face potentially significant migration work, particularly where servers relied on Sampling or persistent session machinery, but updated SDKs for Python, TypeScript, Go, and C# support both old and new protocol versions during a transition period that includes beta tooling, validation, and minimum deprecation windows.
Track how attackers are adapting to this technology.
2 events from the most recent confirmed update back to the earliest known activity.
On 2026-07-28, the Agentic AI Foundation released a major Model Context Protocol specification update that replaces MCP’s legacy stateful architecture with a more stateless model for easier enterprise deployment. The release also added a formal feature lifecycle and deprecation policy, SEP 2468 issuer validation to mitigate OAuth Mixup Attacks, and support for enterprise-managed authorization, asynchronous tasks, header-based routing, and cacheable list results.
The Model Context Protocol is reported to be moving from a session-based design to a stateless, request-centric architecture in a release candidate scheduled for July 28, 2026. The update also introduces features such as Multi Round-Trip Requests, routable transport headers, OAuth 2.1/OpenID Connect-based authorization, interactive MCP Apps, and caching improvements while deprecating several legacy features.
Follow how adversaries are adapting to this technology, and where it touches your stack today.
4 references tracked. Mallory keeps watching after this page renders.
scworld.com
Open sourcetheregister.com
Open sourcethenewstack.io
Open sourceinfoworld.com
Open sourceMap indicators from this story to your assets and identify affected systems in minutes.
Every observed campaign, victim, and pivot linked to actors named in this story.
Malware, exploits, and IOCs connected to the activity described here.
YARA, Sigma, and Snort rules deployed to your SIEM as soon as they’re published.
Get matching new stories delivered to your team as they break — not the next morning.
Ask questions about this story and take action on the answers.
Other stories Mallory is tracking that overlap on entities, sources, or topic labels.
The **Model Context Protocol (MCP)** has been updated to a fully stateless design in the `2026-07-28` specification, removing required sessions, the `initialize` handshake, and the `Mcp-Session-Id` header so MCP servers can run as standard HTTP services without sticky-session infrastructure. The update also replaces stream-dependent elicitation with **Multi Round-Trip Requests**, adds MCP-specific HTTP headers for gateway and security controls, and tightens authorization through issuer identification and canonical resource audience handling. Cloudflare said its Agents SDK and Workers OAuth Provider already support the new model, and cited production adoption by **Sentry** and **Linear**. At the same time, major vendors including **OpenAI, AWS, Cursor, GitHub, Microsoft, and Vercel** backed **Agent Plugins 1.0.0**, a vendor-neutral format for packaging MCP servers and agent skills for use across clients and runtimes. The push for interoperability comes with growing security concerns: researchers published new **Nuclei** templates to detect publicly exposed AI agent configuration files such as `CLAUDE.md`, `AGENTS.md`, Cursor rules, and `vscode-mcp.json`, warning that misconfigured web roots can leak internal workflows, tool settings, and project conventions as organizations expand AI agent deployments.
Aug 8, 2026
A change to the Model Context Protocol (**MCP**) stateless core did not remove session risk so much as relocate it to application-layer identifiers that large language models must preserve across turns. The reported design leaves servers relying on models to correctly carry and replay values such as basket IDs, browser IDs, and tenant-linked handles, creating opportunities for silent misrouting, cross-tenant actions, workflow hijacking, and unauthorized data access when a model drops context or uses the wrong identifier. The warning is reinforced by research on multi-turn degradation in LLMs, including the paper *LLMs Get Lost In Multi-Turn Conversation*, which found models struggle as conversations lengthen and information must be retained accurately across turns. The report also cites a Red Hat incident in which an agent chose the wrong account despite the correct identifier being present in prompt context, underscoring that valid-looking but incorrect requests can still succeed. Recommended defenses include per-request authorization of handles, short-lived high-entropy identifiers, idempotency keys, and testing agent workflows at deeper conversation turn counts.
Aug 13, 2026
Researchers at the University of Hong Kong have introduced NetMCP, a platform that enhances the Model Context Protocol (MCP) by adding network awareness to the tool routing process for large language models (LLMs). This approach allows LLMs to select external tools and data sources not only based on semantic relevance but also on real-time network performance metrics such as latency and server availability, addressing reliability and speed issues in large-scale, production environments. The NetMCP platform simulates various network conditions to test and optimize these routing algorithms, highlighting the trade-offs between performance and security when integrating network metrics into LLM agent operations. The Model Context Protocol itself, developed by Anthropic, is an open standard that enables AI-LLM applications to interact directly with external data sources through a client-server architecture. MCP servers act as proxies, providing structured access to external services and tools, and are supported by extensive SDKs and documentation. The integration of network-aware routing into MCP, as demonstrated by NetMCP, raises new security considerations for organizations deploying LLMs, as the expanded connectivity and dynamic routing may introduce additional attack surfaces and operational complexities.
Jul 12, 2026