Unclear What marking a tool as coming from the remote session changes about its permission prompt is not stated.
MCP tools are tools supplied by outside servers. When Claude Code decides whether a tool call needs permission, it can now mark an MCP tool as coming from the remote session. A tool is marked this way when it passes a check and one of these holds:
- its server is on a short list of allowed servers, and a first server switch is on
- a second server switch is on, which is off unless it is switched on remotely
In readings taken before this release, the flag server returned on for the first switch, for this site's account and for the anonymous baseline.
This lets Anthropic change from the server how permissions for MCP tools are handled in remote sessions.
tengu_deep_dusk Gate removed from the codeThis release deleted the gate from the code while it was still reading on for the account this site reads, so the code path no longer asks a flag before running.
This account: on · anonymous baseline: on · compiled default in v2.1.314: not a boolean we can read
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.
tengu_buzzing_pelican Not enough to sayNothing here resolved what this flag was doing on this version, so nothing here should be read as on or off.
This account: no value returned · anonymous baseline: no value returned · compiled default in v2.1.314: 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 v2.1.314. It isn't a statement about your account. What a flag value here can and cannot tell you
The code path no longer asks a flag before it runs.
What marking a tool as coming from the remote session changes about its permission prompt is not stated.