Claude Code subagents missed a slow MCP server's tools. Version 2.1.311 fixes it.
By Lior AharonovFounder, 7IT Solutions ·
What happened
Claude Code 2.1.311 reached npm on 26 October. Its changelog fixes subagents being unable to use MCP tools from servers that finish connecting after the subagent starts, and an interrupt that waited for a timeout while an MCP server had not answered a resource read. The stable channel is still 2.1.308.
Why it matters
Picture your server finishing its handshake a moment late. The main agent sees your tools, but the subagent it hands the job to does not, and reaches for something else. Connect time was quietly deciding who got used.
What to do
Measure how long your server takes to finish connecting, from first request to a ready tool list, and cut it where you can. Users on the stable 2.1.308 channel still have the old behaviour.

My take
Lior Aharonov
Founder, 7IT Solutions
Fast startup used to be a nicety. Once agents delegate, it decides whether your server is in the room at all.
Sources
| Claude Code CHANGELOG, 2.1.311 | raw.githubusercontent.com |
| npm registry: @anthropic-ai/claude-code 2.1.311 | registry.npmjs.org |
Researched with AI tools; every fact is checked against the linked sources.