Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [Feature] /mcp reconnect-all: batch restart all MCP servers mid-session

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

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.

Root Cause

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.

Fix Action

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.

RAW_BUFFERClick to expand / collapse

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 #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

  • #43177 — MCP stdio servers never auto-reconnect after disconnect
  • #54136 — Reconnect/restart MCP servers from Claude Code without restart
  • #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

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…
#device allocation#model download#tokenizer error#prompt formatting#chain error

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING

claude-code - 💡(How to fix) Fix [Feature] /mcp reconnect-all: batch restart all MCP servers mid-session