{"version":"2.1.280","anchor":"mcp-rpc-content-redacted-from-tracing-for-memorydynamic-sdk","canonical_anchor":"mcp-rpc-content-redacted-from-tracing-for-memorydynamic-sdk","heading":"MCP RPC content redacted from tracing for memory\/dynamic-SDK tools","tier":"internal","area":"MCP","url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280\/e\/mcp-rpc-content-redacted-from-tracing-for-memorydynamic-sdk","release_url":"https:\/\/changelogs.core-directive.com\/v\/2.1.280","markdown":"### MCP RPC content redacted from tracing for memory\/dynamic-SDK tools\n\nMCP tool-call content is now redacted before being sent to tracing for the memory server and dynamic SDK-scoped tools\n\n**What**\n\nWhen Claude Code sends a tracing span for an MCP (Model Context Protocol) tool call, it now checks whether the tool belongs to the memory server or is a dynamic SDK-scoped MCP tool. If so, the captured content is replaced with a redaction placeholder before it's recorded in the trace.\n\n**Why**\n\nThis prevents potentially sensitive content from memory-server or dynamic SDK tool calls from being captured in tracing data.\n\n- Area: MCP\n- Tier: Under the hood\n- Useful: 1\/5\n- Signal: 1\/5"}