{"version":"2.1.312","anchor":"permission-prompt-tool-path-now-knows-about-mcp-skills","canonical_anchor":"permission-prompt-tool-path-now-knows-about-mcp-skills","heading":"--permission-prompt-tool messages now take MCP skills into account","tier":"notice","area":"MCP","scope":"both","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.312\/e\/permission-prompt-tool-path-now-knows-about-mcp-skills","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.312","markdown":"### `--permission-prompt-tool` messages now take MCP skills into account\n\nThe message built for a `--permission-prompt-tool` now knows when the tool asking for permission is an MCP skill\n\n**Unclear.** How the message wording changes for MCP skills is not shown.\n\n**What**\n\n`--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.\n\n**Why**\n\nThe wording of permission prompts for MCP skills is likely to differ from other prompts.\n\n- Area: MCP\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: both\n- Heads-up: no"}