What this error means
v2.1.142 disconnects on remote-SSH after extension update — claude binary accumulation + MCP server flapping is a Claude Code failure pattern reported for developers trying to fix claude code disconnecting during remote-ssh sessions after upgrading to v2.1.142, with binary accumulation and mcp server flapping. Based on the imported evidence, treat this as a tool-specific troubleshooting page rather than a generic API error.
Why this happens
GitHub issue #59552 filed 2026-05-15, labeled bug+platform:linux+area:mcp+area:ide+platform:vscode. Multi-hour large-context sessions disconnect after v2.1.142 upgrade. Category mapped to AI Coding Tools per Claude Code -> AI Coding Tools rule.
Common causes
- GitHub issue #59552 filed 2026-05-15, labeled bug+platform:linux+area:mcp+area:ide+platform:vscode. Multi-hour large-context sessions disconnect after v2.1.142 upgrade. Category mapped to AI Coding Tools per Claude Code -> AI Coding Tools rule.
Quick fixes
- Confirm the exact error signature matches
v2.1.142 disconnects on remote-SSH after extension update — claude binary accumulation + MCP server flapping. - Check the Claude Code account, local tool state, and provider configuration involved in the failing workflow.
- Compare the failing environment with a known working setup, then change one configuration value at a time.
Platform/tool-specific checks
- Verify the command, editor, extension, or API client that produced the error.
- Compare local settings with CI, deployment, or editor-level settings when the error appears in only one environment.
- Avoid deleting credentials, local model data, or project settings until the failing scope is clear.
Step-by-step troubleshooting
- Capture the exact error message and the command, editor action, or request that triggered it.
- Check whether the failure is account/auth, quota/rate, model/provider, local runtime, or deployment configuration.
- Review the source evidence below and compare it with your environment.
- Apply one change at a time and rerun the smallest failing action.
- Keep the working fix documented for the team or deployment environment.
How to prevent it
- Keep provider/tool configuration documented.
- Record non-secret diagnostics such as tool version, provider name, model name, and command path.
- Add a lightweight check before CI or production workflows depend on the tool.