[Feature] /mcp reconnect-all: batch restart all MCP servers mid-session

[javiermoralestealium]

Summary

When running Claude Code with many MCP servers (10+), network drops (VPN reconnects, SASE proxy resets, travel WiFi) disconnect multiple stdio servers simultaneously. Currently there's no way to reconnect them all at once — you have to run /mcp and retry each one individually.

Current behavior

• /mcp shows status of all servers and allows individual retry
• HTTP/SSE servers auto-reconnect with exponential backoff (up to 5 attempts)
• Stdio servers never auto-reconnect (see MCP stdio servers never auto-reconnect after disconnect #43177)
• After a network event, you have to manually reconnect each server one at a time

Requested behavior

A command like /mcp reconnect-all or /mcp restart that:

1. Kills and restarts all stdio MCP server processes
2. Re-initiates connections to all HTTP/SSE servers
3. Reports status (success/failure count) once complete

Use case

I run 12+ MCP servers (Slack, Atlassian, Panther, OpsGenie, Okta, AWS, Glean, n8n, Snyk, etc.) for security operations. VPN reconnects happen multiple times per day (corporate SASE + AWS VPN). Each reconnect currently requires 5-12 individual /mcp retries, which breaks flow significantly.

Workaround

Currently the best workaround is exiting the session and starting fresh with --continue, which reconnects all servers on startup. But this loses any in-progress context compression state and is disruptive.

Related issues

• MCP stdio servers never auto-reconnect after disconnect #43177 — MCP stdio servers never auto-reconnect after disconnect
• [Feature] Reconnect/restart MCP servers from Claude Code in Claude Desktop without Cmd+Q (expose /mcp UI or auto-reconnect) #54136 — Reconnect/restart MCP servers from Claude Code without restart
• MCP OAuth tokens expire frequently, requiring manual /mcp reconnect #43789 — OAuth tokens expire, requiring manual reconnect

Environment

• Claude Code CLI on macOS
• 12 MCP servers (mix of stdio and SSE)
• Network: Corporate SASE (Fortra) + AWS VPN = frequent drops

[github-actions]

Found 1 possible duplicate issue:

1. [Feature Request] Bulk MCP server reconnection for multi-server disconnect scenarios #51561

This issue will be automatically closed as a duplicate in 3 days.

• If your issue is a duplicate, please close it and 👍 the existing issue instead
• To prevent auto-closure, add a comment or 👎 this comment

🤖 Generated with Claude Code

[sophymarine]

A batch reconnect command makes sense here, but the tricky part is observability when some servers come back and others do not. It would help if /mcp reconnect-all reported per-server outcomes in a machine-readable way, not just a single success/failure summary, so downstream tooling can decide whether to retry or surface partial health. I’d also keep the command idempotent and explicit about ordering, since a mid-session restart can otherwise create confusing state transitions for attached tools and hooks. A small status table in the CLI output would make support much easier.

[localden]

Thank you for your report — we are currently in the process of triaging MCP-related issues and this one appears to describe the same problem as #51561. To keep the discussion and any fix in one place, we're consolidating into that issue and closing this one. If you have logs, repro steps, or environment details that aren't already covered in #51561, please add them there — it'll help us track this down faster.

[github-actions]

This issue has been automatically locked since it was closed and has not had any activity for 7 days. If you're experiencing a similar issue, please file a new issue and reference this one if it's relevant.