{"version":"2.1.302","anchor":"mcp-tool-result-meta-claudeendturnhonorsstophooks-inert","canonical_anchor":"mcp-tool-result-meta-claudeendturnhonorsstophooks-inert","heading":"Groundwork for letting MCP tools respect stop hooks, currently switched off","tier":"soon","area":"Hooks","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.302\/e\/mcp-tool-result-meta-claudeendturnhonorsstophooks-inert","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.302","markdown":"### Groundwork for letting MCP tools respect stop hooks, currently switched off\n\nCode for a marker that would let MCP tool results respect stop hooks is in place, but it is hard-wired off and does nothing yet\n\n**What**\n\nMCP (Model Context Protocol) servers are outside programs that give Claude extra tools. Stop hooks are your own commands that run when Claude is about to finish its turn. Claude Code now contains code for a `claude\/endTurnHonorsStopHooks` marker on MCP tool results. The switch that would turn it on always says no, so nothing changes yet.\n\n**Why**\n\nIt prepares for a future where an MCP tool asking to end Claude's turn still lets your stop hooks run.\n\n- Area: Hooks\n- Names: `claude\/endTurnHonorsStopHooks`\n- Tier: Nothing to try yet\n- Useful: 4\/5\n- Signal: 4\/5\n- Scope: individual\n- Heads-up: no\n- Present in the build but not switched on"}