{"version":"2.1.319","anchor":"mcp-task-input-errors-no-longer-echo-server-supplied-text","canonical_anchor":"mcp-task-input-errors-no-longer-echo-server-supplied-text","heading":"MCP task input errors no longer repeat the server's own text","tier":"notice","area":"MCP","scope":"individual","heads_up":false,"url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319\/e\/mcp-task-input-errors-no-longer-echo-server-supplied-text","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.319","markdown":"### MCP task input errors no longer repeat the server's own text\n\nErrors about MCP task input requests now list only fault codes, not the text or input key the server sent\n\n**What**\n\nMCP servers are add-on programs that give Claude Code extra tools, and some run long jobs called tasks that can ask you for input. When one of these input requests fails, or a server sends back a task status Claude Code cannot read, the error now lists only the fault codes. It no longer includes the error text or the input key the server supplied.\n\nWhen a server asks for a kind of input Claude Code does not support, Claude Code now shows a fixed message saying so, and logs only the length of the key and the method.\n\n**Why**\n\nAn untrusted MCP server can no longer slip its own wording into Claude Code's logs or into error messages the model reads.\n\n- Flag `tengu_mcp_url_elicitation`: Not enough to say (read for one account on one subscription tier against v2.1.319; this account: no value returned, anonymous baseline: no value returned, compiled default: on) These values were read against a different version of Claude Code, so treat them as the nearest reading available instead of one taken on this release.\n- Area: MCP\n- Tier: You'll notice\n- Useful: 1\/5\n- Signal: 1\/5\n- Scope: individual\n- Heads-up: no"}