canUseTool
A Claude Code settings key, read out of the shipped bundle. No mined inventory carries it: everything below comes from what this site has written about it.
Background and forked agents now run your permission callback even when a hook says allow, and deny rules win.
Not Anthropic's. This is the line from the earliest changelog entry here that named it, v2.1.222.
In the changelogs
13Releases whose published page names canUseTool.
-
v2.1.284
Agent SDK runs can keep going after the result while background work finishes
The Agent SDK now ends a run when Claude Code reports it is idle, which can mean waiting up to 10 minutes after the result
found in this entry's text
-
v2.1.281
SDK canUseTool receives requiresUserInteraction, serverPrompt and computerFolder
The SDK's canUseTool callback can now receive requiresUserInteraction, serverPrompt and computerFolder when a permission request carries them
found in this entry's text, named in this entry
-
v2.1.281
New can_use_tool fields server_prompt and computer_folder, passed through to the SDK host
Permission requests sent to SDK hosts can carry two new internal fields, serverPrompt and computerFolder, set only by the session service
found in this entry's text, named in this entry
-
v2.1.280
SDK/plugin session scope gains savedAgentMessages and requestMessages callbacks
The SDK's internal session bridge gained savedAgentMessages and requestMessages callbacks
found in this entry's text
-
v2.1.275
Session-teardown 'leave questions standing' path has no caller
New leaveQuestionsStanding path rejects pending permission questions with a teardown message but nothing calls it yet
found in this entry's text
-
v2.1.269
SendMessage cross-machine permission check now passes a detached
askcallbackSendMessage's cross-machine permission check now uses a detached approval callback instead of passing context and canUseTool directly
found in this entry's text
-
v2.1.259
Permission-prompt-tool routing gets a bypass for an explicit "none" sentinel
A permission-prompt tool named none now routes through an ask-based fallback resolver instead of the MCP prompt tool.
found in this entry's text
-
v2.1.223
permission_denied events fire even without a permission prompt
Headless and SDK runs now report permission denials even when no prompt was ever shown.
named in this entry, found in this entry's text
-
v2.1.222
Forked and background agent queries require canUseTool by default
Background and forked agents now run your permission callback even when a hook says allow, and deny rules win.
named in this entry, found in this entry's text
- v2.1.216
- v2.1.207
-
v2.1.119
SDK Enhancements
found in this entry's text
-
v2.0.69
Prompt Suggestion Code Refactoring
found in this entry's text
First cited
1The earliest release whose published evidence quoted canUseTool was v2.1.119, 23 Apr 2026. That is the oldest release this project wrote about it, so it is a floor on the name's age and not the release that introduced it. It is not a presence reading: which builds carried the name is the table below.
Presence across releases
0The miner has never read a build containing this name. It is here because a changelog entry of ours names it, which is evidence that it existed and not evidence of which releases carried it. The inventory starts at v2.1.138 and everything older than that was never mined.
Read out of the published npm bundle release by release, and out of Anthropic's own documentation as this site captured it. Nothing on this page is a description anybody here wrote about what the settings key does. All settings keys.