Model Context Protocol spec (2026-07-28 revision)

MCP's anniversary spec revision makes the protocol stateless, cacheable, and header-routable, with hardened OAuth and a formal async Tasks extension.

Model Context Protocol · Agent frameworks and orchestration · framework

Published in Feed

Overview

Published July 28, 2026, this MCP revision removes the initialize/initialized handshake and session IDs for self-describing stateless requests, adds Multi Round-Trip Requests (MRTR) for confirmations without held-open streams, and moves method/tool names into HTTP headers (Mcp-Method, Mcp-Name) for gateway/WAF routing. It hardens auth with RFC 9207 issuer validation and Client ID Metadata Documents replacing Dynamic Client Registration, adds ttlMs/cacheScope caching hints, formalizes the Tasks extension for long-running async operations, and deprecates Roots/Sampling/Logging with a 12-month support window. All Tier 1 SDKs (TypeScript, Python, Go, C#) support it at launch; Rust support is in beta.

This is a sourced directory entry. Features and capabilities are reported in the linked sources; this entry does not document independent Aymorphic testing.

Key features

  • Stateless request/response core, no session IDs or handshake
  • Multi Round-Trip Requests (MRTR) replace server-initiated confirmations
  • Header-based routing (Mcp-Method, Mcp-Name) for gateways and WAFs
  • RFC 9207 issuer validation plus Client ID Metadata Documents replace Dynamic Client Registration
  • Tasks extension formalized for long-running async operations

Use cases

  • Building MCP gateways/routers needing cacheable, statelessly-routable requests
  • Enterprises needing stricter OAuth/issuer validation for MCP servers
  • Long-running agentic tool calls needing async polling instead of held-open connections

Pricing

Not applicable (open protocol specification).

Pricing reflects the source record and may change. Confirm current terms with the provider.

Dates and sources

Released
28 Jul 2026
Record updated
23 Sept 2026
Record last checked
23 Sept 2026

Explore the Feed

Other entries filed under agent frameworks and orchestration; inclusion does not imply equivalent features.

  • Workday Agent Harness

    Workday's generally available environment for building enterprise agents with isolated runtimes, memory and governed HR/finance data access.

  • Agent Bricks

    Databricks' no-code system for building and auto-optimizing domain-specific AI agents, now generally available with synthetic eval-data generation and multi-agent orchestration.

  • Muse Agents SDK

    Meta's open-source SDK for building and orchestrating multi-agent systems on top of its Muse model family.

Browse the Feed