Unclear It is not clear whether anything in this release sends MCP skill approval requests.
Remote Control lets you follow and steer a Claude Code session from another device. Some permission requests sent over it come with a label saying what needs your action. Before, only the question and plan tools and tools needing user interaction got one. Requests to approve an MCP skill now get one too. An MCP skill is a skill provided by an MCP server, an outside program that gives Claude Code extra tools.
The label is the skill's display name, or its tool name if it has no display name, and it has no further text.
This sits behind a setting that is off unless it is switched on remotely. When this site's account checked, the server returned it as on, though no check has been made under this release yet.
A device following a session through Remote Control can show a named prompt when an MCP skill needs approval, instead of an unlabelled one.
tengu_bridge_requires_action_details Off by default, switched on for this accountThe shipped code defaults this off, and the flag server returned on for the one account this site reads on this version. That is the reading that makes the entry above worth a second look, and it still says nothing about your account.
This account: on · anonymous baseline: on · compiled default in v2.1.312: off
These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.
Read once, for one account on one subscription tier, against v2.1.312. It isn't a statement about your account. What a flag value here can and cannot tell you
It is not clear whether anything in this release sends MCP skill approval requests.