Create

Sign in to ReadmeX

or

How we handle your data: Privacy Policy

ReadmeX

Your AI reading companion

What would you like to catch up on?

Pick a briefing, or ask your own question.

Your community and people briefings stay personal to you.

Story

Mastra ships @mastra/mcp 2.0 with MCP 2026-07-28 sessionless spec support

AI summary

Mastra says @mastra/mcp 2.0.0 now supports the MCP 2026-07-28 specification, which removes the initialize handshake (SEP-2575) and protocol-level sessions including the Mcp-Session-Id header (SEP-2567), so every request is self-contained. Mastra says MCP servers built with it can now run across load-balanced instances or on serverless platforms that scale to zero; previously a session pinned a client to the instance that issued its session ID, and requests routed elsewhere behind a load balancer could return 400 session not found errors, with sticky sessions or a shared store such as Redis as workarounds. The post also describes new Mcp-Method and Mcp-Name headers, cache hints on list results, a server/discover method and requestState for asking users for input mid-call, notes that tasks are now an official extension Mastra is still investigating, and says the spec deprecates HTTP+SSE transport, roots, sampling, logging and OAuth Dynamic Client Registration, which @mastra/mcp 2.0 has already removed.

In-depth insight

According to Mastra, sessionless requests remove the need for sticky sessions or a shared session store when scaling Mastra-built MCP servers, which the vendor says lets them scale like any other HTTP service.

Mastra now supports the MCP 2026-07-28 specification with @mastra/mcp ^2.0.0. The new spec removes server sessions, so every request is self-contained. If you build MCP servers with Mastra, you can now scale them like any other HTTP service, across load-balanced instances, or on serverless platforms that scale to zero.

How MCP 1.0 worked

In the previous MCP spec, a client opened every connection with an initialize request. The server created a session, sent back a session ID, and every following request had to include it.

This pinned the client to whichever server instance issued the session. If you ran multiple servers behind a load balancer, a request could be routed to an instance that didn't recognize the session ID, resulting in 400 session not found errors.

The workarounds were sticky sessions or a shared session store like Redis. Both solutions worked, but they added complexity, latency, and potentially cost.

Your browser does not support the video tag.

#Mastra#@mastra/mcp#@mastra/core#Model Context Protocol

Original · 5 min readRead the original
Group chat

No comments yet. Start the conversation.