claude-code - 💡(How to fix) Fix [Feature] Reconnect/restart MCP servers from Claude Code in Claude Desktop without Cmd+Q (expose /mcp UI or auto-reconnect) [2 comments, 2 participants]

Setup

Claude Code now runs embedded inside the new Claude Desktop. When an MCP server dies, hangs, or needs to pick up a config change, there is no in-session way to recover from the Desktop UI:

• The CLI's /mcp slash command (which exposes per-server reconnect / status / OAuth re-auth) isn't reachable from the Desktop CC pane. The general missing-slash-commands gap is tracked in #45399, but /mcp deserves a specific call-out because it's not just a convenience — it's the only recovery affordance.
• Auto-reconnect is broken for stdio (#43177) and there's no reload-on-config-change anywhere (#40059), so even waiting it out doesn't help.
• The current workaround is Cmd+Q + reopen Claude Desktop, which kills every session in the app, not just the broken one. Users with multiple Desktop CC sessions, or with Desktop sessions sharing context with mobile / Cowork, lose all of that to recover one stuck MCP.

What I'm asking for

Any one of the following would close the gap. They're listed in increasing scope; even (1) alone would unblock most users:

1. Expose /mcp (or an equivalent affordance) inside the Desktop CC pane. A right-click on a server name, a status-bar icon, a button in a settings drawer — anything clickable that triggers the same reconnect path the CLI's /mcp already supports.
2. Auto-reconnect on idle-disconnect for stdio MCP servers in Desktop. The pattern reported repeatedly in #43177 (transport closed after ~60s idle, server process still healthy, next call hangs 4 min) is especially painful in Desktop because the Cmd+Q reset is so heavy. The one-line fix proposed in #43177 would carry over.
3. A "Restart MCP servers" menu item in Desktop's app menu that re-reads .mcp.json / ~/.claude.json and reconnects without tearing down the rest of the app — essentially #40059's /mcp-reload but exposed as a Desktop UI action.

Bonus: surface a status indicator (green/red dot) per MCP server in the Desktop CC pane so users can see which one is broken without opening the CLI to find out.

Repro

1. Open Claude Desktop with Claude Code integration enabled.
2. Configure any stdio MCP server in .mcp.json or via claude mcp add.
3. Use it for a few tool calls, then idle the chat for ~60+ seconds.
4. Next tool call hangs, eventually fails with a transport error.
5. There is no UI in Desktop to reconnect just that server. The only path back to a working MCP is Cmd+Q + reopen Claude Desktop, which terminates every other open session.

Same flow happens after editing .mcp.json to add a new server, or after an OAuth token expires (#43789) — none of these have a Desktop-side recovery affordance.

Environment

• Claude Desktop with Claude Code integration (latest)
• macOS (also reported on Windows in adjacent issues)
• Multiple stdio MCP servers configured

Related issues

These are adjacent but none of them, alone or together, close the specific Desktop-UI gap:

• #43177 — stdio MCP servers never auto-reconnect (root cause + 1-line fix identified)
• #40059 — Allow reloading MCP servers without restarting the session (CLI-focused)
• #45933 — Add McpReconnect tool so the model can reconnect failed MCP servers
• #51561 — Bulk MCP server reconnection for multi-server disconnect scenarios
• #42627 — Programmatic MCP server reconnection (disable/re-enable via hook or API)
• #53125 — Remote Control: allow MCP server reload / process restart from a remote session
• #53298 — Reconnect action unreachable for mcpServers entries added by direct ~/.claude.json edit
• #43789 — MCP OAuth tokens expire frequently, requiring manual /mcp reconnect
• #45399 — Desktop app missing slash commands available in CLI (general; this issue is the MCP-specific subset)
• #46623 — HTTP OAuth MCP servers silently fail in Claude Code inside Claude Desktop (silent-failure adjacent)
• #47538 — Local MCP tool calls approved but never forwarded to server (Desktop + Claude Code in Desktop)

Filing this separately because the Desktop-specific UI affordance for MCP reconnect is the missing piece across all of the above — fixing /mcp parity in Desktop, or adding any of the alternatives in "What I'm asking for," would benefit users regardless of which underlying disconnect cause they hit.