Summary
mcp-publisher status (v1.8.0) consistently fails with a 504 Gateway Time-out (nginx HTML error page) after ~60s when updating a server version's status against registry.modelcontextprotocol.io. Publishing new servers via POST /v0/publish works fine from the same environments.
Repro
From GitHub Actions (login github-oidc, org namespace):
./mcp-publisher status --status deleted --yes --all-versions \
--message "Superseded by io.contextstream/mcp" io.github.contextstream/mcp
Output:
This will update 1 version(s) of io.github.contextstream/mcp:
0.5.35: active → deleted
Error: server returned status 504: <html>
<head><title>504 Gateway Time-out</title></head>
...
- 5 attempts over ~1 hour on 2026-07-13 (19:33–20:35 UTC), all identical 504s after ~60s.
- Fetching the versions list (the step right before) succeeds each time, so reads are healthy; only the status-change call times out.
- Same-day publishes (
POST /v0/publish) from both DNS auth and github-oidc succeeded immediately, so this looks specific to the edit/status path (possibly a slow query or lock behind the PUT /v0/servers/{name}/versions/{version} handler exceeding the 60s proxy timeout).
Happy to provide timestamps/request details if useful.
🤖 Generated with Claude Code
Summary
mcp-publisher status(v1.8.0) consistently fails with a 504 Gateway Time-out (nginx HTML error page) after ~60s when updating a server version's status againstregistry.modelcontextprotocol.io. Publishing new servers viaPOST /v0/publishworks fine from the same environments.Repro
From GitHub Actions (
login github-oidc, org namespace):Output:
POST /v0/publish) from both DNS auth and github-oidc succeeded immediately, so this looks specific to the edit/status path (possibly a slow query or lock behind thePUT /v0/servers/{name}/versions/{version}handler exceeding the 60s proxy timeout).Happy to provide timestamps/request details if useful.
🤖 Generated with Claude Code