-
Notifications
You must be signed in to change notification settings - Fork 111
Error calling tool xxx: context deadline exceeded #11
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
Comments
Same issue here! What is that all about? |
I'm also getting this when I use this configuration: {
"mcpServers": {
"filesystem": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-filesystem",
"/tmp/demo"
]
}
}
} |
The main issue here is that sometime it takes too long for the LLM to respond, so either you dont use a deadline or extend it to a proper duration. |
I had same issue in macOS. Issue resolved after updating to the latest version of node and npm. |
I have implemented a very simple tools that returns a string containing some raw Prometheus metrics.
When testing the server with
npx @modelcontextprotocol/inspector
the server runs perfectly and is very fast.I am calling:
./mcphost_Linux_x86_64/mcphost --config mcp.json --model ollama:qwen2.5:3b
The output is:
When I am asking a question releated to the metrics, I am getting the following error and and reply....
Even when enabling --debug, I have no clue of what is going on.
Thank-you for your assistance.
The text was updated successfully, but these errors were encountered: