Why doesn't the MCP Trigger node URL include /sse endpoint? (v1.99.1, deployed on Hostinger)

[zhe_wang]

Hi everyone,

I’m running into a strange issue with the MCP Trigger node in n8n.

When I create an MCP Trigger node, it generates a URL like this:
https://mydomain.hostinger.com/mcp/7583cb44-xxxx-xxxx-xxxx-xxxxxxxxxxxx

But as far as I understand, the actual endpoint required by the MCP client is the /sse subpath, like:
https://mydomain.hostinger.com/mcp/7583cb44-xxxx-xxxx-xxxx-xxxxxxxxxxxx/sse

However, the generated URL in n8n doesn’t include /sse by default, and I haven’t found any clear explanation in the documentation or tutorials (I watched quite a few videos but none mentioned this).

Has anyone experienced the same thing?

• Is this the expected behavior?
• Should I always manually add /sse to the URL myself?
• Or is this a misconfiguration in my deployment?

n8n version: 1.99.1
Deployment: Hosted via Docker on Hostinger cloud server
MCP Trigger node works if I manually add /sse, but it’s not obvious from the UI.

Would appreciate any insights or best practices!

Thanks in advance,
Alex

[nikhilkuria]

Hi Alex,

Welcome to the community forums
Everything is fine with your deployment and this is by design.
In 1.99, we introduced support for Streamable HTTP transport and the /sse postfix was removed as part of this.

This means, nothing changes for you and you can use the URL directly without making any changes. The mcp clients will be able to use it.
Hope it helps.

Warm Regards,
Nikhil
n8n team

[zhe_wang]

Hi, dear Nikhil,

thanks for the confirming !
I have tried using the following method from the doc, it works both for local and cloud host scenario!

{
“mcpServers”: {
“n8n”: {
“command”: “npx”,
“args”: [
“mcp-remote”,
“<MCP_URL>”,
“–header”,
“Authorization: Bearer ${AUTH_TOKEN}”
],
“env”: {
“AUTH_TOKEN”: “<MCP_BEARER_TOKEN>”
}
}
}
}