--permission-prompt-tool messages now take MCP skills into…

--permission-prompt-tool messages now take MCP skills into account

The message built for a --permission-prompt-tool now knows when the tool asking for permission is an MCP skill

You'll noticeTier: how much it should matter to you

2Useful: my rating, 1 to 5

2Signal: worth watching, 1 to 5

MCPArea: what it touches

ImprovementsKind: in v2.1.312, 27 Oct 26

ImprovementsSection of the release

Unclear How the message wording changes for MCP skills is not shown.

What

--permission-prompt-tool names an MCP tool that answers permission prompts when Claude Code runs non-interactively. MCP is a way to connect Claude Code to outside tools. The message Claude Code builds for that tool now also notes whether the action being asked about comes from an MCP skill. Before, it only noted whether the wording was for a host.

Why

The wording of permission prompts for MCP skills is likely to differ from other prompts.

How sure we are

Something disagreesSomething we can check disagrees with this entry, or the writer said they could not settle it.

The writer flagged doubtHow the message wording changes for MCP skills is not shown.

See this entry in the whole of v2.1.312 →

The build it came inv2.1.312

27 Oct 2026 · 265 entries, this one is #71.

Use it now10
You'll notice136
Nothing to try yet9
Under the hood110

Either side of it

v2.1.311Older

Open the release →

Names in this entry

cli--permission-prompt-tool
Specify an MCP tool to handle permission prompts in non-interactive mode. Pass the full name, such as mcp__<server>__<tool>, of a tool on an MCP server that the run loads. Claude Code waits for that tool's MCP server to connect before running the first turn, up to the MCP_TIMEOUT startup timeout, 30 seconds by default. The prompt tool can't approve an MCP tool marked as requiring user interaction: Claude Code converts an allow result for one to a deny. This restriction requires Claude Code v2.1.199 or later

Is this right?