Skip to content

docs(ai-agents): document MCP connection timeout behavior #742

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.

Sign up for GitHub

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

Closed
mintlify wants to merge 1 commit into from
Closed

docs(ai-agents): document MCP connection timeout behavior #742

Changes from all commits
Commits
Show all changes
1 commit
Select commit
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
14 changes: 14 additions & 0 deletions guides/ai-agents/mcp-servers.mdx
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -140,6 +140,20 @@ The agent pulls the data from your warehouse, generates the summary, and appends

The agent searches Confluence for the canonical definition, then answers using both the doc and your data.

## Troubleshooting

### "The MCP server took too long to respond and was disconnected"

Lightdash applies a 20-second timeout when connecting to an MCP server and when discovering its tools. If the server is unreachable or hangs, it is marked as errored with this message and you can retry once the server is healthy. When attached to an agent, a slow server only stalls itself — other MCP servers still load and respond.

If you self-host Lightdash and need a longer (or shorter) timeout — for example because an internal MCP server is behind a slow proxy — set `MCP_CONNECTION_TIMEOUT_MS` on your deployment:

```bash
MCP_CONNECTION_TIMEOUT_MS=30000
```

The value is in milliseconds and defaults to `20000`. Lightdash Cloud uses the default.

## Security

- All credentials (bearer tokens and OAuth tokens) are encrypted at rest.
Expand Down
Loading