live wire
▸JAVA · Quarkus 4.0.0.Beta1 moves to Java 21, adds HTTP/3 and starts extension migration (Oct. 1)Quarkus▸SECURITY · X41 shows shared /dev/shm can turn Envoy hot restart into cross-container lateral movementX41 D-Sec▸DATA · AWS and Red Hat map Confluent Platform on ROSA with HCP, CFK and OpenShift security controlsAWS IBM & Red Hat▸API · Red Hat resolves intermittent 3scale API Manager latencyRed Hat Status▸AI · IBM shows Maximo workflows exposed as approval-gated MCP tools on OpenShiftIBM Community▸AI · vLLM adds day-zero NVIDIA Vera Rubin support and reports 7.8× per-GPU throughputvLLM▸INTEGRATION · Apache Camel 4.23 makes Kamelets visible to AI tooling and validationApache Camel▸SECURITY · OpenShift 4.14.75 fixes five CVEs, including two SQLite code-execution flawsRed Hat Customer Portal▸SUPPLY CHAIN · Red Hat maps CRA-ready open source practices as EU reporting rules take effectRed Hat Blog▸AI · Red Hat AI Inference on IBM Cloud adds an OpenAI-compatible Embeddings APIIBM Cloud▸API · Red Hat investigates degraded 3scale API Management SaaS APIsRed Hat Status▸PLATFORM · Red Hat and Cloudera validate a 100-VM analytics stack on OpenShift VirtualizationRed Hat Blog▸DEVELOPER HUB · Red Hat maps a four-zone, quota-aware Dev Spaces architectureRed Hat Developer▸INTEGRATION · Camel 4.23 teaches agent tools to discover and validate KameletsApache Camel▸JAVA · Quarkus 4.0.0.Beta1 moves to Java 21, adds HTTP/3 and starts extension migration (Oct. 1)Quarkus▸SECURITY · X41 shows shared /dev/shm can turn Envoy hot restart into cross-container lateral movementX41 D-Sec▸DATA · AWS and Red Hat map Confluent Platform on ROSA with HCP, CFK and OpenShift security controlsAWS IBM & Red Hat▸API · Red Hat resolves intermittent 3scale API Manager latencyRed Hat Status▸AI · IBM shows Maximo workflows exposed as approval-gated MCP tools on OpenShiftIBM Community▸AI · vLLM adds day-zero NVIDIA Vera Rubin support and reports 7.8× per-GPU throughputvLLM▸INTEGRATION · Apache Camel 4.23 makes Kamelets visible to AI tooling and validationApache Camel▸SECURITY · OpenShift 4.14.75 fixes five CVEs, including two SQLite code-execution flawsRed Hat Customer Portal▸SUPPLY CHAIN · Red Hat maps CRA-ready open source practices as EU reporting rules take effectRed Hat Blog▸AI · Red Hat AI Inference on IBM Cloud adds an OpenAI-compatible Embeddings APIIBM Cloud▸API · Red Hat investigates degraded 3scale API Management SaaS APIsRed Hat Status▸PLATFORM · Red Hat and Cloudera validate a 100-VM analytics stack on OpenShift VirtualizationRed Hat Blog▸DEVELOPER HUB · Red Hat maps a four-zone, quota-aware Dev Spaces architectureRed Hat Developer▸INTEGRATION · Camel 4.23 teaches agent tools to discover and validate KameletsApache Camel
upstreambeat.ai
newsJAVA

Quarkus MCP Server 2.0 makes stateless MCP deployable without a flag day

The extension accepts the July 2026 stateless protocol and legacy session-based clients on one endpoint, giving platform teams a staged migration path.

Legacy and stateless MCP requests share one Quarkus endpoint during migration.
AI-generated illustration
By The News Desk· Sep 26, 2026the quick take — two AI hosts go live when you do

Quarkus has added support for the Model Context Protocol’s stateless transport model without forcing existing clients to migrate at the same time. The 2.0.x line of Quarkus MCP Server handles the July 28, 2026 protocol revision and older session-based versions on the same endpoint, according to the project’s September 21 engineering post.

That compatibility detail matters more than the version number. Under the earlier design, a client initialized a session, received an identifier and had to keep talking to the same server instance—or rely on sticky routing or a shared session store. The current MCP specification instead defines stateless, self-contained JSON-RPC requests with capability negotiation performed per request.

A migration path rather than a cutover

Quarkus MCP Server inspects the protocol version carried in the request metadata and HTTP headers. Requests using the July 2026 revision are handled through a transient connection for the life of the call; older requests fall back to the established stateful path. Both modes remain available at the same URL.

For application teams, that means clients can move individually rather than through a coordinated cutover. Quarkus LangChain4j clients can discover server capabilities and prefer the new revision automatically, while operators can pin either the stateless or legacy protocol during a migration.

The operational payoff is straightforward: any available server instance can process a self-contained request. That removes protocol-level pressure for session affinity when horizontally scaling an MCP service behind a load balancer.

Server-to-client calls change shape

Stateless operation also changes features that previously depended on a persistent channel. Sampling, elicitation and roots can no longer assume that a server will call back across an open session. The new protocol represents those interactions as multi-round-trip requests: a server returns an input_required result, and the client retries the original request with the requested data attached.

Quarkus exposes both paths through its APIs so tools can detect whether server-initiated requests are supported and use the appropriate flow. Subscriptions similarly move from the older resources/subscribe approach to a filtered subscriptions/listen stream for stateless clients.

What teams need to do

Existing Quarkus MCP Server users can adopt the 2.0.x release and begin accepting newer stateless clients without rewriting their tool methods. Code that uses sampling, elicitation or roots needs closer review because it may have to handle both callback and retry-based interactions.

The project also says it runs the official MCP conformance suite in continuous integration. Support for the revision’s extension mechanism is planned for Quarkus MCP Server 2.1.0 rather than included in the current line.

Filed by The News Desk. Corrections: desk@upstreambeat.ai · Our standards →

comments · 0

    Comments are moderated before they appear. Your email is used once to confirm it is you — never shown, never sold. Corrections and questions get an answer from the desk when we have one.