{"version":"2.1.319","anchor":"artifact-mcp-ask-first-wrapper-and-the-sandbox-remote-tool-i","canonical_anchor":"artifact-mcp-ask-first-wrapper-and-the-sandbox-remote-tool-i","heading":"Some artifact MCP results can carry an extra note for Claude","tier":"internal","area":"Artifacts","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319\/e\/artifact-mcp-ask-first-wrapper-and-the-sandbox-remote-tool-i","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319","markdown":"### Some artifact MCP results can carry an extra note for Claude\n\nClaude Code can now add a text note to the start of certain artifact MCP results, which changes what the model sees\n\n**Unclear.** It is not clear which artifact MCP calls get the extra text, what the text says, or whether anything switches it on.\n\n**What**\n\nMCP servers are outside programs that give Claude Code extra tools. For some calls to an artifact MCP tool, Claude Code can now place an extra block of text at the start of the result before the model reads it.\n\nSeparately, the usage data Claude Code records about remote tools now includes the interface version both sides agreed on and a count of interfaces that did not match.\n\n**Why**\n\nThe extra text changes what the model sees when it gets an artifact MCP result back, which can change how it responds.\n\n- Area: Artifacts\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 2\/5\n- Scope: individual\n- Heads-up: no"}