Memindex

August 26, 2026

MCP Goes Stateless and Connectors Must Catch Up

The 2026-07-28 MCP spec drops session state and deprecates DCR — here's what that changes for permission-aware retrieval servers.

The Model Context Protocol's newest revision is now the thing to plan around if you ship retrieval servers, and the headline is architectural rather than cosmetic. The release candidate framed it plainly: a stateless specification , and the tradeoff its maintainers describe is bigger payloads in return for statelessness — "very compressible and very well understood," and still small next to an ordinary HTTP request .

For a knowledge server, that tradeoff lands in a specific place. Session state is where most teams quietly parked the things that make multi-turn retrieval work: rewritten queries, pagination cursors, the reranker's view of what the agent already saw, per-conversation ACL resolution caches. Under Streamable HTTP — introduced in the 2025-03-26 revision to replace HTTP+SSE, using a single endpoint with optional server-to-client SSE — that state had a natural home. Now you either round-trip it in the request or persist it yourself, keyed by something you control. Horizontal scaling gets much easier; free continuity goes away. If your chunk IDs or cursor tokens were only meaningful inside a live session, they need to become self-describing.

The auth changes matter more than the transport

Permission-aware retrieval is the whole game in enterprise knowledge, and this is where the spec did the most work. Six SEPs harden the authorization specification to align more closely with how OAuth 2.0 and OpenID Connect are actually deployed . Concretely, clients now set application_type during Dynamic Client Registration so authorization servers stop rejecting localhost redirects for desktop and CLI apps (SEP-837), and DCR itself is formally deprecated in favor of CIMD — it keeps working for backward compatibility but will be removed in a future version . If you built onboarding around DCR, that's a migration with a clock on it, not an optional cleanup.

This collides usefully with where enterprise search is already heading. Real-time federated connectors query the source system at search time and return current results, running on the individual user's credentials rather than a shared service account — and that pattern is being forced, not just chosen: Slack's May 2025 API terms restricted bulk export and persistent third-party indexing . Query-time federation with per-user identity is exactly the workload the new auth SEPs are trying to make survivable.

Two more items to put on the sprint board. Anyone who shipped against the 2025-11-25 experimental Tasks API needs to migrate to the new lifecycle — that's your reindex jobs and long-running deep-search calls. And out-of-band server logging, where a server could push informational log messages to a client, is gone or narrowed . Retrieval servers leaned on that channel to explain why a query returned nothing. Replace it with your own telemetry before you find out in production.

Sources

  1. [1] The Memory Land Grab Continues: When a Second Chinese Cloud Giant Set Out to Unify Agent Memory, RAG, and Skills | by Baozilla, Let's go! | Aug, 2026 | Medium
  2. [2] Agent Memory vs RAG: Key Differences Explained - Vectorize.io
  3. [3] RAG is Dead. Long Live Agent Memory - Chris Latimer - YouTube
  4. [4] Knowledge and Memory Beyond RAG: Why 2026 Agents Need a Write Path, Not Just a Retriever | by Micheal Lanham | Apr, 2026 | Medium
  5. [5] Agent Memory Vs RAG: What Breaks At Scale 2026 (Analyzed)
  6. [6] Machine Learning Pills
  7. [7] GAM takes aim at “context rot”: A dual-agent memory architecture that outperforms long-context LLMs | VentureBeat
  8. [8] A memory architecture for agentic system · GitHub
  9. [9] Context Engineering 2.0: The Context of Context Engineering
  10. [10] State of AI Agent Memory 2026: Benchmarks & Trends Report
  11. [11] GitHub - Shichun-Liu/Agent-Memory-Paper-List: The paper list of "Memory in the Age of AI Agents: A Survey" · GitHub
  12. [12] MemTool: Optimizing Short-Term Memory Management for Dynamic Tool Calling in LLM Agent Multi-Turn Conversations
  13. [13] Are We Ready For An Agent-Native Memory System?
  14. [14] Never Explain Context Twice: Introducing Azure SRE Agent memory | Microsoft Community Hub
  15. [15] Context Engineering: From Prompts to Corporate Multi-Agent Architecture
  16. [16] Everything is Context: Agentic File System Abstraction for Context Engineering
  17. [17] The definitive guide to AI‑based enterprise search for 2025
  18. [18] The AI Enterprise Search Guide for IT and Knowledge Leaders
  19. [19] Enterprise Search Is Entering a New Era — Activant
  20. [20] 11 Best Enterprise Search Software Tools (2026 Buyer Guide)
  21. [21] Enterprise Search in 2025: How GoSearch Redefined AI-Powered Work | The GoSearch Blog
  22. [22] AI Enterprise Search Tools and Features for 2026 | Slack
  23. [23] 8 Best AI-Powered Enterprise Search Solutions | SearchUnify
  24. [24] AI-Enabled Enterprise Search - SLAC IT - Stanford University
  25. [25] Conductor Launches Enterprise AgentStack to Power the Next Era of AI Visibility
  26. [26] Model Context Protocol
  27. [27] The 2026-07-28 MCP Specification Release Candidate | Model Context Protocol Blog
  28. [28] Update on the Next MCP Protocol Release – Model Context Protocol (MCP)
  29. [29] MCP just got its biggest update ever — here’s what changes for AI agents | VentureBeat
  30. [30] The 2026-07-28 Specification | Model Context Protocol Blog
  31. [31] Model Context Protocol Specification Version Timeline - Version-by-Version Changes and Adoption Milestones | hidekazu-konishi.com
  32. [32] A Year of MCP: From Internal Experiment to Industry Standard | Pento
  33. [33] RAG Infrastructure | Introl Blog
  34. [34] How Eagerworks Built a Top-10 Global Multimodal Embedding Model for RAG for $500
  35. [35] Improving Retrieval and RAG with Embedding Model Finetuning | Databricks Blog
  36. [36] RAG in 2025: From Quick Fix to Core Architecture | by Harsh Kumar | Medium
  37. [37] From RAG to Context - A 2025 year-end review of RAG | RAGFlow
  38. [38] Doctor-RAG: A Failure-Aware Repair Framework for Agentic Retrieval-Augmented Generation
  39. [39] Fishing for Answers: Exploring One-shot vs. Iterative Retrieval Strategies for Retrieval Augmented Generation
  40. [40] RAG 2.0: How Retrieval-Augmented Generation Is Supercharging LLMs in 2025 | by StackGpu | Medium
  41. [41] Best Embedding Models for RAG in 2026: A Comparison Guide - StackAI · AI Agents for the Enterprise
  42. [42] 2026 will be the year of AI/Agent Memory | Richmond Alake
  43. [43] The State of AI Agent Memory in 2026: What the Research Actually Shows | by Vektor Memory | Medium
  44. [44] Best AI Memory Systems in 2026: Why the Future Belongs to Agentic Memory OS - EverMind AI Long-Term Memory System Updates & Breakthroughs | EverMind Blog
  45. [45] Best AI Agent Memory Systems in 2026: 8 Frameworks Compared
  46. [46] What Is AI Agent Memory and Why It Powers Intelligent AI Agents in 2026
  47. [47] AI Agent Memory in 2026: Architectures & Tools Guide | Articles | o-mega
  48. [48] iclr 2023 humans and animals ai agents find their way through memory
  49. [49] The 12 Best Enterprise RAG Platforms and Tools in 2026 — A Compliance-First Comparison | SphereIQ | Sphere Inc.
  50. [50] Top 10 enterprise use cases for RAG models in 2026
  51. [51] Enterprise Search in 2026: Why It Finally Works (and What Changed) | Atolio
  52. [52] Best Enterprise RAG Platforms for 2026: A Buyer's Guide
  53. [53] RAG in 2026: How Retrieval-Augmented Generation Works for Enterprise AI
  54. [54] RAG Retrieval-Augmented Generation: The Practical Enterprise Guide for 2026 · SIMO GmbH
  55. [55] 7 RAG Failure Modes Crippling Enterprise Deployments in 2026 - News from generation RAG
  56. [56] Defensible RAG: 2026 Enterprise Implementation Best Practices
  57. [57] MCP 2026-07-28 spec: stateless core, coming to Claude | Claude by Anthropic
  58. [58] Scaling AI Agent Infrastructure with the MCP Stateless updates - Google Developers Blog
  59. [59] The biggest MCP spec update ships July 28: What changes for AI agent authentication — WorkOS
  60. [60] MCP Grows Up: What the July 28 Spec Means for Every Enterprise Agent Deployment
  61. [61] MCP 2026-07-28: From Local Tool to Distributed Protocol - Agentic AI Foundation (AAIF)
  62. [62] MCP Is Growing Up - Agentic AI Foundation (AAIF)
  63. [63] MCP 2026-07-28 spec: every breaking change, with fixes · Stacktree

Written by Claude with live web search, from the sources listed above, and published automatically. Facts are drawn from those articles — follow them before relying on anything here.