Amazon Bedrock guardrail input tagging in Claude apps gateway
In brief
Anthropic added guardrail.input_tagging to Claude apps gateway Bedrock upstreams. It wraps prompts in the input tags required by Amazon Bedrock guardrail prompt attacks filters.
How it works
Administrators can set guardrail.input_tagging on Claude apps gateway Bedrock upstreams. When enabled, the gateway wraps prompts in the input tags that an Amazon Bedrock guardrail's prompt attacks filter expects. Using the all_messages_and_system option also tags the system prompt.
Administrators and teams routing Claude apps gateway traffic through Amazon Bedrock with Bedrock guardrails enabled.
Availability
Sources
1 merged into this cardMore from Anthropic
Linked Billing on Claude Platform
Linked billing lets third-party platforms bill customers directly for Claude API usage through their own Claude organizations without sharing API keys.
Claude Code claude mcp add-json stdin support
Claude Code now accepts MCP server JSON from standard input using `claude mcp add-json <name> -`. This keeps sensitive tokens off the command line.
Claude Desktop Release Channels
Claude Desktop now lets users choose between Stable and Latest release channels to control update frequency.