{"version":"2.1.265","anchor":"mcp-tool-calls-gain-artifact-server-argresult-hooks","canonical_anchor":"mcp-tool-calls-gain-artifact-server-argresult-hooks","heading":"MCP tool calls gain artifact-server arg\/result hooks","tier":"internal","area":"MCP","scope":null,"heads_up":null,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265\/e\/mcp-tool-calls-gain-artifact-server-argresult-hooks","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.265","markdown":"### MCP tool calls gain artifact-server arg\/result hooks\n\nMCP tool calls to artifact servers now pass through argument-rewriting and result-observing hooks\n\n**What**\n\nWhen Claude Code calls a tool on an MCP server (a way for Claude Code to talk to external tools and data sources), it now runs the call's arguments through an `argsForCall` step before sending them, and runs the response through an `observeResult` step afterward. A specific handler for the 'artifact' class of MCP servers uses this to rewrite arguments on management calls, and, for `list_artifacts` calls, to record telemetry including a count of shared artifacts.\n\n**Why**\n\nThis gives Claude Code a hook point to adjust artifact-related MCP calls and to gather usage data on artifact listings, without changing what the tool call looks like to the server itself.\n\n- Area: MCP\n- Tier: Under the hood\n- Useful: 2\/5\n- Signal: 1\/5"}