What probably matters to youSection of the release
What
The limit on how much output an MCP tool may return still reads the MAX_MCP_OUTPUT_TOKENS environment variable first, then a server-side config value, then a built-in default. The environment value is no longer checked for being a finite number before use.
Details
Server config comes from tengu_velvet_ibis, whose fallback is an empty object, so with no server value the built-in default applies.
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.
Confirmed sinceAnthropic's documentation has since written up MAX_MCP_OUTPUT_TOKENS, on Build an MCP server for Claude.| Maximum tool result size | \~150,000 characters | 25,000 tokens, configurable with `MAX_MCP_OUTPUT_TOKENS` |connectors/building/indexsee the edit
What has happened since
Flag reading movedThe flag server now returns [] for tengu_velvet_ibis, read as this account.A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
Flag reading movedThe flag server now returns nothing at all, having stopped carrying it for tengu_velvet_ibis, read as this account.A reading is one sample. Claude Code evaluates its flags remotely, so no client sees the targeting rule behind a value and this says nothing about your account.
