I'd made the shift to HTTP/Stateless from MCP a few months ago. It's the right thing to do IMHO. Reliability up, problems down. TOON support is natural, if desired, etc.
My only question is how do you handle channels in the architecture now. From what I saw in Claude Code, shifting to a totally http world has some timeout issues if a server drops out and comes back. Because of that I'm stuck writing stubs for my internal use MCP, this is fine for me, but if you are cleaning up semantics: Understanding how we expect clients to act around failure would really help, the story.
dend 1 hours ago [-]
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!
dan-kwiat 27 minutes ago [-]
Great work! Any word on when to expect support across claude clients?
cidd 37 minutes ago [-]
When will java sdk come out with latest changes from spec?
checker 1 hours ago [-]
Thank you for your work! I was looking forward to the stateless update.
Oras 52 minutes ago [-]
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?
dan-kwiat 29 minutes ago [-]
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.
firasd 1 hours ago [-]
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
djhworld 1 hours ago [-]
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
varmabudharaju 1 hours ago [-]
are they coming up with an alternative? i use them to monitor workflows that takes days and now i have to make some changes
dend 1 hours ago [-]
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!
landver 29 minutes ago [-]
[flagged]
rupatiwari25 25 minutes ago [-]
[dead]
Rendered at 19:55:25 GMT+0000 (Coordinated Universal Time) with Vercel.
My only question is how do you handle channels in the architecture now. From what I saw in Claude Code, shifting to a totally http world has some timeout issues if a server drops out and comes back. Because of that I'm stuck writing stubs for my internal use MCP, this is fine for me, but if you are cleaning up semantics: Understanding how we expect clients to act around failure would really help, the story.
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?
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
e.g. mymcpserver.com/tools/call?mcp-method=search