{"version":"2.1.312","anchor":"remote-permission-requests-can-come-from-mcp-skill-tools-mc","canonical_anchor":"remote-permission-requests-can-come-from-mcp-skill-tools-mc","heading":"Permission requests from MCP skills are described and relayed differently","tier":"notice","area":"MCP","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.312\/e\/remote-permission-requests-can-come-from-mcp-skill-tools-mc","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.312","markdown":"### Permission requests from MCP skills are described and relayed differently\n\nPermission prompts for MCP skills now show the skill's summary, offer no always-allow option, and are not relayed to the skill's own server\n\n**Unclear.** It is not clear whether any tool calls in this release are actually marked as coming from an MCP skill.\n\n**What**\n\nMCP (Model Context Protocol) servers are outside programs that give Claude extra tools and skills. When a tool call that comes from an MCP skill needs your permission and the request is passed to you remotely, Claude Code now handles it differently:\n\n- The prompt describes the action with the skill's summary instead of the tool's standard description.\n\n- The prompt does not offer an option to always allow the action.\n\n- Channel servers are connected servers that pass permission prompts on to you somewhere else. The server that owns the skill no longer receives the prompt.\n\n- An \"allow\" answer from the server that owns the skill is ignored.\n\nBefore, every permission prompt used the tool's standard description, and every connected channel server received it.\n\n**Why**\n\nThis changes who can approve an MCP skill's actions. The server that provides a skill can no longer approve that skill's own requests.\n\n- Area: MCP\n- Tier: You'll notice\n- Useful: 2\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}