Seems like this can be closed now, @ashwin-ant?
I didn't see anything in the changelog but I saw this today:

Usage: claude mcp add [options] <name> <commandOrUrl> [args...]

Add a server

Options:
  -s, --scope <scope>          Configuration scope (local, user, or project) (default: "local")
  -t, --transport <transport>  Transport type (stdio, sse, http) (default: "stdio")
  -e, --env <env...>           Set environment variables (e.g. -e KEY=value)
  -H, --header <header...>     Set HTTP headers for SSE transport (e.g. -H "X-Api-Key: abc123" -H "X-Custom: value")
  -h, --help                   Display help for command

And --transport http seems to work properly. 🙂

"Set HTTP headers for SSE transport" description shouldn't be SSE only, as it is used for HTTP as well.

Also https://docs.anthropic.com/en/docs/claude-code/mcp doesn't have it documented yet

Originally posted by @garrett-hopper in #1387

I tried Claude Code with a Streamable HTTP MCP Server and call a long-running streaming mcp tool, only the first streaming output is displayed. Subsequent streaming outputs are not shown in the Claude Code, even though the tool continues running (the connection is alive).

Expected Behavior Claude Code should display all streaming outputs from long-running MCP tools in real-time, allowing users to see the progress and intermediate results as they are generated.

Does anyone know how to deal with this?