What probably matters to youSection of the release
What
MCP servers are add-ons that give Claude Code extra tools, and they can send instructions that are added to the conversation. The context usage breakdown now counts those instructions, including instruction blocks added on your side, and shows them as "MCP server instructions" beside "MCP tools". Before, they had no line of their own.
The entry above is what we published on the day. These lines were added later, as Anthropic's own pages caught up, and they sit beside the original rather than replacing it.
Added sinceA small documentation edit on claude-on-vertex-ai touched a line naming /context after this was published.Claude Fable 5.1, Claude Fable 5, Claude Opus 5.5, Claude Opus 5, Claude Opus 4.8, Claude Opus 4.7, Claude Opus 4.6, Claude Sonnet 5.5, Claude Sonnet 5, and Claude Sonnet 4.6 have a [1M-token context window](https://platform.claude.com/doc…build-with-claude/claude-on-vertex-aisee the edit
Confirmed sinceAnthropic's documentation has since written up /context, on Model configuration.| **`sonnet[1m]`** | Uses Sonnet with a [1 million token context window](https://platform.claude.com/docs/en/build-with-claude/context-windows#context-window-sizes-by-model) for long sessions. No effect when `sonnet` already resolves to So…model-configsee the edit
How sure we are
Two sources agreeTwo things we can check say the same as this entry.
Anthropic's documentation agreesAnthropic's documentation has since written up /context, on Model configuration.
Anthropic's release notes agreeFixed /context not counting MCP server instructions: they now appear as their own row and count toward the total
