{"version":"2.1.280","anchor":"mcp-tools-can-be-hidden-from-the-model-and-marked-as-account","canonical_anchor":"mcp-tools-can-be-hidden-from-the-model-and-marked-as-account","heading":"MCP tools can be hidden from the model and marked as account-memory-backed","tier":"use","area":"MCP","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/mcp-tools-can-be-hidden-from-the-model-and-marked-as-account","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### MCP tools can be hidden from the model and marked as account-memory-backed\n\nMCP tools can now be hidden from the model and flagged as backed by account memory\n\n**What**\n\nMCP (Model Context Protocol, the standard Claude Code uses to connect external tools) tools can now carry extra metadata that controls how they show up:\n\n- A hidden-from-model marker that removes the tool from the list the model sees, so it never gets called even though it's registered.\n\n- A `uiMeta` payload carried alongside the tool definition.\n\n- An `accountMemory` flag marking tools that come from account-memory servers.\n\nBuilding on the earlier `_meta` fields that let MCP tool authors set result-size caps and similar behavior, this adds the ability to keep a tool registered but invisible to the model, and to distinguish account-memory-backed tools from others.\n\n**Why**\n\nThis lets MCP server authors register tools that exist for bookkeeping or UI purposes without cluttering the model's tool list or risking it calling them by mistake.\n\n- Area: MCP\n- Tier: Use it now\n- Useful: 3\/5\n- Signal: 2\/5"}