{"version":"2.1.323","anchor":"tool-use-hook-runs-now-receive-agentidagenttype-mcp-calls","canonical_anchor":"tool-use-hook-runs-now-receive-agentidagenttype-mcp-calls","heading":"Tool hooks receive more details about agents and MCP calls","tier":"use","area":"Hooks","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323\/e\/tool-use-hook-runs-now-receive-agentidagenttype-mcp-calls","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.323","markdown":"### Tool hooks receive more details about agents and MCP calls\n\nTool-use hook runs now get the agent's ID and type, and MCP tool calls carry more labels, including whether a call is not read-only\n\n**Unclear.** It is not stated whether these new details reach hooks you configure yourself.\n\n**What**\n\nHooks are steps that run automatically around a tool call, which is any action Claude takes such as running a command. Claude Code now passes more detail along to them:\n\n- The ID and type of the agent that made the call.\n\n- For MCP tools, from outside services, a flag when the call is not read-only.\n\n- For MCP tools, labels for some kinds of server, such as a hosted Chrome server, an artifacts server, or one linked to a plugin.\n\nTool errors are also now sorted into interrupted or cancelled.\n\n**Why**\n\nThis gives hook steps a finer view of which agent acted and what kind of MCP server it used.\n\n- Area: Hooks\n- Tier: Use it now\n- Useful: 3\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}