#Is anyone else having connection issues

1 messages · Page 1 of 1 (latest)

neon cometBOT
#

support request from @vale grotto (flagged by @hearty dune) in #🚀│welcome

Is anyone else having connection issues with their MCP endpoint hitting timeouts? None of my MCP server are responding anymore. No changes to code. I have not hit any ratelimits. Done 4 hours of troubelshooting on my end. All is perfect. Is Composio MCP down or whats going on? System going hot?

Original message link: #🚀│welcome message

beep boop, I've moved this conversation here so the support team can get back to you sooner.

Could you please share your debugging info if you have not already? https://docs.composio.dev/resources/debugging-info

Welcome to Composio | Composio Docs
hearty dune
#

hey @vale grotto can you share the debugging info and i can check we can check what is happening

sick scaffold
vale grotto
#

well, its been a good 24 hours of troubleshooting now, when we updated from v52 to v53 we had to change get_server to mcp_generate. This added some runtime but it was not an issue at the time. Then all of a sudden. It started hanging indefinatley. I still have this issue. We worked around it by bypassing the entire Composio SDK and built 400 lines of custom code just to see if this was on the Composio side or not.

We are running Vercel AI SDK with Composio SDK - 3 MCP servers with aprox 120 tools. Everything is very well done and in good order. And our webapp worked really good, and all of a sudden it started hanging shortly after the update of composio.

I have like 10 docs on this right now and i still havent come to the conclusion on whats happening. I just tried updating to v54 as its EXACTLY what happened to us. We came to the "tool export" and then it hanged.

This is the info from the Agent wrapping everything, and som supabase DB logs: Hope this answers your questions and can help us debug.

#

@hearty dune @sick scaffold got some info for you guys.

sick scaffold
#

thanks for the details, we'll take a look and get back.

vale grotto
#

Let me know if you need more! I'll keep pushing for a few more hours to find out what's going on.

sick scaffold
vale grotto
#

I rebranched and updated every single package, and have updated to the new API, trying the new structure - And all the other SDK's as well. So, we are getting closer. But its still hanging. Yes, I have tried the endpoints with curl and postman and this worked and was fast, but something is off with deno and Composio. Thats where I am at right now. I'll keep you updated. We are getting closer that's for sure. I just want to make sure this is on our end and not yours. When importing into deno, we use @latest, this might be an issue, it worked previously but we are testing pinning the packages right now. And adding comprehensive logging at the endpoints so we will know shortly.

vale grotto
#

Question. How long should it take for and mcp client to be created or initiated like this:

[MCPToolLoader] Using MCP URL: https://apollo.composio.dev/v3/mcp/19a9a16f-c585-4702-b82e-391737e62869?transport=sse&user_id=viralr_content
[MCPToolLoader] Creating MCP client...

Can you see anything that is wrong with this flow in the text doc? We are timing out on the creation of the mcp server. It used to answer really quckly and now it doesnt. I need to know if something has happened on your side or if we have the delays on our side, it doesnt look like it. This entire flow on our side is usually done under 10 seconds.

#

sry, you needed the times not the flow only, check this instead!

sick scaffold
#

It looks like there's an LLM call involved if I'm not wrong, so that depends on the task and model's speed.

vale grotto
#

The experimental_createMCPClient() in the Vercel AI SDK hangs because it doesn't respond to server "ping" messages over Server-Sent Events (SSE). This causes the connection to time out, preventing tools from executing. This is a know issue, so you should revert the clause that Vercel works with Composio. Becasue Vercel doesnt work with SSE and experimental_createMCPClient. There is no ping-pong going on. Only ping.

The solution is a fork of Vercel ai SDK and a wrapper of the client.

The reason it worked for about a week. Or "now and then":

Likely one (or a combo) of these changed mid-stream:

Dependency update: A patch/minor release of Vercel AI SDK, Composio, or a transitive SSE/EventSource polyfill changed behavior (e.g., stricter heartbeat/ping handling). Even “non-breaking” updates can alter timing.
Server-side tightening: Composio MCP servers may have enabled/shortened ping/idle timeouts. Your client not replying to pings would start failing once the server enforced them.
Environment/network shifts: Edge runtimes (Supabase/Render) can change keep‑alive, idle TCP, or proxy timeouts. A redeploy, region move, or infra tweak can surface previously masked bugs.
Load pattern: Under light load, connections survived long enough despite missing pongs; once traffic/latency increased, the lack of ping/pong started causing disconnects/hangs.
Code path variance: Small logic/config changes (creating more clients per request, longer tool runs, different model/tools) increased connection duration, triggering the heartbeat issue.
In short: the client has a latent ping/pong gap; a routine update or runtime change flipped conditions so the server now expects heartbeats your client doesn’t send, so it began hanging.

That was a good 48 hour troubleshooting getting to this point.

#

So, anyone using Vercel ai SDK with Composio should do HTTP requests only if they want to go the safe path! They will loose streaming, but it will work 100%. Because the SSE can work, or stop working at any time, with any minor tweaks, updates or network load. Real shady problem. Hope this helps.