slack-mcp-server slow/hangs on large Slack workspaces (e.g. Kubernetes Slack)
Why does slack-mcp-server (korotovsky/slack-mcp-server) appear to hang or not work with enterprise/large Slack workspaces like kubernetes.slack.com? The server starts but never shows 'Provider booted successfully' and no error is shown.
Originally asked on GitHub: https://github.com/korotovsky/slack-mcp-server/issues/1
4 answers
Fixed in the repository on 2025-04-26 per the maintainer. The root cause: slack-mcp-server prefetches every workspace user at startup, so huge workspaces take a long time to become ready.
On workspaces like kubernetes.slack.com (~200k users), the maintainer's log showed the first boot taking about 10 minutes and ending with:
mcp-server-1 | 2025/04/26 16:54:26 Wrote 213801 users to cache ".users_cache.json" mcp-server-1 | 2025/04/26 16:54:26 Provider booted successfully.The fix caches the user list to a local JSON file, so the first boot is still slow on very large workspaces, but subsequent runs should be quick. If the server appears to hang, wait for the
Provider booted successfully.line before using it with Claude, especially on community Slack workspaces with tens or hundreds of thousands of members. The maintainer deliberately avoided undocumented Slack APIs for now, so the one-time 10-minute boot is the expected trade-off.Did this work for you?What a GitHub user tried on GitHub (Outcome unclear)
Reported that the server "doesn't seem to work" against an enterprise Slack workspace (https://slack.com/enterprise (opens external site)), with no further detail provided.
Source: https://github.com/korotovsky/slack-mcp-server/issues/1 (opens external site)
Did this work for you?What @kaovilai tried on GitHub (Outcome unclear)
Suggested reproducing on the Kubernetes community Slack workspace via communityinviter.com/apps/kubernetes/community.
Did this work for you?What @korotovsky tried on GitHub (Worked)
Maintainer applied a fix for the user-fetch step. The server then wrote 213,801 users to .users_cache.json and reached 'Provider booted successfully' after about 10 minutes on kubernetes.slack.com; later boots use the cache.
Did this work for you?
Related questions
- Why does slack-mcp-server with XOXC/XOXD tokens fail with invalid_auth while caching users?
- Why does slack-mcp-server channels_list return only CSV headers while message search works?
- When will slack-mcp-server ship the merged Slack bot token support (v1.1.27)?
- Slack MCP channels_list returns only 6 channels despite token having 15+ channel access
- slack-mcp-server: message text shows raw Slack user IDs instead of display names