Skip to content
Forums
Forums
How To
Trouble connecting ...
 
Notifications
Clear all

Trouble connecting to MCP Server

 
How To
Last Post by system 2 months ago
5 Posts
4 Users
0 Reactions
4 Views
RSS
motoneurona
 motoneurona
(@motoneurona)
Posts: 2
New Member
Topic starter
 

Hi,

My MCP server has unexpectedly stopped functioning. It was operating correctly, but for an unknown reason, it has ceased to work.

I’ve reproduced the issue in a more straightforward workflow, as illustrated in the image below:

Captura de pantalla 2025-05-22 095240

Captura de pantalla 2025-05-22 0952402013×1266 160 KB

The Agent is entering into a loop.

The configuration appears to be correct. The console output is as follows:

McpClientTool: Failed to connect to MCP Server
Error in sub-node MCP Cal.com
McpClientTool: Failed to connect to MCP Server
Error in sub-node MCP Client
Received request for unknown webhook: The requested webhook "sheet/sse" is not registered.
McpClientTool: Failed to connect to MCP Server
Error in sub-node MCP Client
Received request for unknown webhook: The requested webhook "sheet/sse" is not registered.
Received request for unknown webhook: This webhook is not registered for HEAD requests. Did you mean to make a GET request?

I have attempted multiple times to modify the test/prod mode, paths, tools, and other settings, but without success.

Any assistance would be greatly appreciated!

  • callin.io version: 1.93
  • Database (default: SQLite):
  • callin.io EXECUTIONS_PROCESS setting (default: own, main):
  • Running callin.io via (Docker, npm, callin.io cloud, desktop app): Docker
  • Operating system: Ubuntu 22
 
Posted : 22/05/2025 7:59 am
Gallo_AIA
 Gallo_AIA
(@gallo_aia)
Posts: 22
Eminent Member
 

Hello!
Welcome to the callin.io community!

Your workflows are likely fine; the problem seems to be in how SSE/webhook connections are handled by your hosting environment. Adjusting the execution mode and checking the reverse proxy behavior should help.

→ Similar issues can be found in the callin.io community and Coolify GitHub

What you can try?

  1. Switch execution mode (if possible)

    If you’re using EXECUTIONS_MODE=queue, try changing it to:

    EXECUTIONS_MODE=own

    This allows callin.io to manage SSE/webhook registration directly.

  2. Check your reverse proxy

    If you’re deploying with Coolify or have NGINX/Traefik in front of callin.io:

    • Make sure /sse and /webhook/* routes are not cached, rewritten, or blocked.
    • Ensure SSE connections are supported.

  3. Try running the same flow locally

    To rule out infrastructure issues:

    • Run callin.io locally.
    • Activate the MCP Server workflow first, then the MCP Client/Agent.
    • If it works locally, the issue is definitely with your cloud/proxy configuration.

Let me know!

 
Posted : 22/05/2025 8:28 am
motoneurona
 motoneurona
(@motoneurona)
Posts: 2
New Member
Topic starter
 

Resolved! The issue stemmed from Traefik. I'm using EasyPanel, and version 2.16 introduced a bug that was fixed in version 2.17 (the default compress middleware was removed due to a bug in Traefik).

After upgrading, everything is functioning correctly!

Thanks for your time!

 
Posted : 22/05/2025 9:04 am
Timilehin_Adesanya
 Timilehin_Adesanya
(@timilehin_adesanya)
Posts: 1
New Member
 

I'm running callin.io in Docker on an IONOS server behind the built-in Nginx reverse proxy. When my Voice AI instance calls the MCP Server Trigger endpoint, I'm encountering:

502 Bad Gateway
failed to connect to MCP server

My suspicion is that GZIP or buffering might be interfering with the SSE connection. I've added a custom Nginx block to disable compression, but the error persists.

Configuration:

  • Plesk edition: IONOS
  • Web servers: Apache + Nginx (reverse proxy)

  • Docker container:

    • Image: n8nio/callin.io
    • Port mapping: 127.0.0.1:9001→5678

  • Custom Nginx include: /var/www/vhosts/system/n8n.domain.com/conf/vhost_nginx.conf

location ^~ /mcp/ {
    proxy_pass            http://127.0.0.1:5678/mcp/; 
    proxy_http_version   1.1;
    proxy_set_header     Connection "";
    proxy_buffering      off;
    proxy_cache          off;
    proxy_read_timeout   3600s;
    proxy_send_timeout   3600s;
    gzip                 off;
}

Request:

What might I be overlooking in my Nginx or Plesk setup that's preventing the MCP SSE endpoint from connecting successfully without causing a 502 error? Could you offer any suggestions on the next steps or additional directives to try?

 
Posted : 26/05/2025 1:12 am
system
 system
(@system)
Posts: 332
Reputable Member
 

This discussion was automatically closed 7 days following the last response. New replies are no longer permitted.

 
Posted : 02/06/2025 1:13 am
Forum Jump:
  Previous Topic
Next Topic  
Share: