← Back to Dashboard
1. CRITICAL: April 2026 STDIO RCE2. Agentic AI Foundation (AAIF)3. MCP Release Candidate (May 2026)4. MCP Stable Release (July 2026): What Shipped5. MCP 2026 Roadmap, Working Groups & Enterprise SOE/AOE
MCP Release Candidate (May 2026)
The Largest Revision Since Launch
On May 22, 2026, the MCP working groups announced the MCP Release Candidate (RC) - the biggest single revision to the protocol since its original launch. The final release shipped on schedule as the stable 2026-07-28 protocol version.
⚠️ Breaking Changes: The RC includes breaking changes from earlier versions. Migration documentation is available in the RC specification. Plan your upgrade path now.
✅ Confirmed Shipped:
2026-07-28 is now the current MCP protocol version, officially superseding 2025-11-25. The next lesson covers exactly what changed between this RC and the final release.Key Architectural Changes
| Change | What It Means | Impact |
|---|---|---|
| Stateless Core | Eliminates sticky sessions and session IDs from the core protocol. MCP servers can now run behind standard round-robin load balancers using plain HTTP. | 🔴 Biggest architectural change - simplifies deployment at scale dramatically |
| Extensions Framework | New capabilities are negotiated as extensions rather than being baked into the core specification. | 🟡 Enables faster iteration without breaking the core protocol |
| Tasks Extension | Formal support for long-running asynchronous operations (evolved from SEP-1686 Tasks Primitive). | 🟢 Critical for agent workflows that span minutes or hours |
| Enhanced Authorization | Aligns MCP auth with modern OAuth 2.1 and OpenID Connect standards. | 🟢 Enterprise-ready SSO and identity federation |
| Formal Deprecation Policy | Establishes long-term stability guarantees with defined deprecation timelines. | 🟢 Confidence for production deployments |
The Stateless Shift - Why It Matters
Before the RC, MCP servers were inherently stateful - each client-server pair maintained a session, requiring sticky routing in load balancers. This made horizontal scaling painful:
// BEFORE (stateful - requires sticky sessions): Client A ──▶ Load Balancer ──▶ Server Instance #3 (pinned) Client B ──▶ Load Balancer ──▶ Server Instance #1 (pinned) // AFTER RC (stateless - standard round-robin): Client A ──▶ Load Balancer ──▶ Any Server Instance Client B ──▶ Load Balancer ──▶ Any Server Instance
With the stateless core, MCP servers are now plain HTTP services that can be deployed, scaled, and load-balanced with existing infrastructure - no special session affinity required.
Migration Checklist
- ☐ Review the RC specification and breaking changes
- ☐ Identify any session-dependent logic in your servers
- ☐ Migrate stateful features to use the new Extensions Framework
- ☐ Update auth flows to align with OAuth 2.1 / OIDC
- ☐ Test against the RC SDK before the July 28 final release
💡 Key Insight: The move to a stateless core is the single most impactful change for production MCP deployments. It means MCP servers can now be treated like any other stateless HTTP microservice - deployed on Kubernetes, Cloud Run, Lambda, or any container platform without special session handling.
🧪 Knowledge Check
Press 1-4 to select1 of 3
What is the single biggest architectural change in the MCP Release Candidate?
New tool types
Eliminating sticky sessions - making the core protocol stateless so servers can run behind standard load balancers
Adding WebSocket support
Changing from JSON to Protocol Buffers