MCP 2026-07-28 Specification: transport going stateless

#1

Post by Eldodi » Tue, Jul 28, 2026, 6:35 PM UTC

MCP 2026-07-28 Specification: transport going stateless
blog.modelcontextprotocol.io

Re: MCP 2026-07-28 Specification: transport going stateless

#2

Post by firasd » Tue, Jul 28, 2026, 6:43 PM UTC

Perfect. The actual tool calls are stateless anyway; when an LLM asks get_my_todos and then asks add_todo it’s not actually holding anything in RAM it’s just text going back into the context window (get_my_todos results) and then another tool call

And even on the server side statefulness is very iffy anyway. How long are you going to hold something in RAM from a client and how long will you hold the connection open

Re: MCP 2026-07-28 Specification: transport going stateless

#3

Post by varmabudharaju » Tue, Jul 28, 2026, 6:46 PM UTC

are they coming up with an alternative? i use them to monitor workflows that takes days and now i have to make some changes

Re: MCP 2026-07-28 Specification: transport going stateless

#4

Post by dend » Tue, Jul 28, 2026, 6:47 PM UTC

Hey folks - one of the Lead Maintainers for MCP. Happy that we got this release out the door today, this is an exciting change for those that wanted to roll out remove MCP servers into serverless hosts. There is, of course, more good stuff packed, so if you have questions or feedback - our team is here to help!

Re: MCP 2026-07-28 Specification: transport going stateless

#5

Post by dend » Tue, Jul 28, 2026, 6:48 PM UTC

varmabudharaju wrote: post #3

are they coming up with an alternative? i use them to monitor workflows that takes days and now i have to make some changes

This protocol change doesn't require you to do anything to existing running MCP code - only if you want to take advantage of new capabilities!

Re: MCP 2026-07-28 Specification: transport going stateless

#6

Post by djhworld » Tue, Jul 28, 2026, 6:49 PM UTC

Are the HTTP headers for method/name etc even needed at this point and just use urls instead?

e.g. mymcpserver.com/tools/call?mcp-method=search

Re: MCP 2026-07-28 Specification: transport going stateless

#7

Post by checker » Tue, Jul 28, 2026, 6:50 PM UTC

dend wrote: post #4

Hey folks - one of the Lead Maintainers for MCP. Happy that we got this release out the door today, this is an exciting change for those that wanted to roll out remove MCP servers into serverless hosts. There is, of course, more good stuff packed, so if you have questions or feedback - our team is here to help!

Thank you for your work! I was looking forward to the stateless update.

Re: MCP 2026-07-28 Specification: transport going stateless

#8

Post by Oras » Tue, Jul 28, 2026, 7:03 PM UTC

dend wrote: post #4

Hey folks - one of the Lead Maintainers for MCP. Happy that we got this release out the door today, this is an exciting change for those that wanted to roll out remove MCP servers into serverless hosts. There is, of course, more good stuff packed, so if you have questions or feedback - our team is here to help!

Thank you!

What’s the best practice for tools where the upstream API only supports basic auth (username/password) and there’s no OBO option? In my case the login returns a token that’s only valid for an hour, so the user has to re-auth after that. Do you stash the credentials on the MCP server and silently refresh, or is there a nicer pattern people are using?

Re: MCP 2026-07-28 Specification: transport going stateless

#9

Post by cidd » Tue, Jul 28, 2026, 7:18 PM UTC

dend wrote: post #4

Hey folks - one of the Lead Maintainers for MCP. Happy that we got this release out the door today, this is an exciting change for those that wanted to roll out remove MCP servers into serverless hosts. There is, of course, more good stuff packed, so if you have questions or feedback - our team is here to help!

When will java sdk come out with latest changes from spec?

Re: MCP 2026-07-28 Specification: transport going stateless

#10

Post by dan-kwiat » Tue, Jul 28, 2026, 7:26 PM UTC

Oras wrote: post #8

dend wrote: post #4

Hey folks - one of the Lead Maintainers for MCP. Happy that we got this release out the door today, this is an exciting change for those that wanted to roll out remove MCP servers into serverless hosts. There is, of course, more good stuff packed, so if you have questions or feedback - our team is here to help!

Thank you! What’s the best practice for tools where the upstream API only supports basic auth (username/password) and there’s no OBO option? In my case the login returns a token that’s only valid for an hour, so the user has to re-auth after that. Do you stash the credentials on the MCP server and silently refresh, or is there a nicer pattern people are using?

URL Elicitation works well if a human is driving the client. Unfortunately MCP client support is patchy but I expect that will change now the protocol is stateless.