diff --git a/apps/web/app/(marketing)/guides/chatgpt-mcp-connector/page.tsx b/apps/web/app/(marketing)/guides/chatgpt-mcp-connector/page.tsx index 18a06ba..477f33c 100644 --- a/apps/web/app/(marketing)/guides/chatgpt-mcp-connector/page.tsx +++ b/apps/web/app/(marketing)/guides/chatgpt-mcp-connector/page.tsx @@ -38,7 +38,9 @@ export default function Page() {

The plan limits, first — because they decide everything

Before writing a single prompt or line of code, check what your ChatGPT plan allows. - OpenAI gates custom MCP connectors by workspace type: + As of mid-2026, OpenAI gates custom MCP connectors by workspace type — verify against + OpenAI's current help docs before committing to a plan, since these limits have + shifted before:

diff --git a/apps/web/app/(marketing)/guides/mcp-transports-explained/page.tsx b/apps/web/app/(marketing)/guides/mcp-transports-explained/page.tsx index 156a76b..925e655 100644 --- a/apps/web/app/(marketing)/guides/mcp-transports-explained/page.tsx +++ b/apps/web/app/(marketing)/guides/mcp-transports-explained/page.tsx @@ -129,7 +129,8 @@ export default function Page() { Spec revision 2025-03-26 replaced HTTP+SSE with Streamable HTTP. The old transport still works where both sides keep supporting it, but the direction is one-way: platforms have been announcing removal dates through 2026 — Atlassian's Rovo MCP server, - for example, set its HTTP+SSE cutoff for June 30, 2026. New servers should not ship it. + for example, announced an HTTP+SSE cutoff of June 30, 2026. New servers should not ship + it.

Streamable HTTP: the current standard

diff --git a/apps/web/app/(marketing)/layout.tsx b/apps/web/app/(marketing)/layout.tsx index 6746330..24edca6 100644 --- a/apps/web/app/(marketing)/layout.tsx +++ b/apps/web/app/(marketing)/layout.tsx @@ -8,7 +8,7 @@ export default function MarketingLayout({ children }: { children: React.ReactNod return (
-
+