Claude Code v2.1.281 adds Bedrock assume_role, guardrails and MCP validation
ashwin-ant · ghdev · 2026-09-24
Anthropic shipped Claude Code v2.1.281, mostly touching the Claude apps gateway and MCP:
- Gateway & security: desktop policy blocks gain blockReadsOutsideWorkingDirectories and disableBypassPermissionsMode; Bedrock upstreams support assumerole (STS into another AWS account, optionally one session per developer) and an Amazon Bedrock guardrail applied to every request.
- MCP: URL-mode elicitation on 2026-07-28 protocol connections lets servers open browser flows; claude plugin validate now flags .mcp. entries that would be silently dropped, undeclared ${userconfig.} refs and insecure URLs.
- Misc: "attribution": false hides commit/PR attribution; /insights estimates how many permission prompts auto mode could have handled; fixes include a crash during API retries and an infinite-retry loop ignoring --max-turns.
More from coding & agent
- Why AI-made dev tools beat one-shot game generation: freedom of process — eschadiol · 2026-09-24
- RealSense VP on AgenticROS: Letting AI Agents Directly Control Physical Robots — chrismatthieu · 2026-09-24
- AWS API Gateway's Hard 10MB Upload Limit and the Presigned URL Fix — _jaydeepkarale · 2026-09-24
- Open-source Pragma gives coding agents a terminal-first workspace with Git worktrees — tech_w0rld · 2026-09-24
- Dev builds dense task annotation system with GPT-6 Astra, ships it as an LLM skill — chris_j_paxton · 2026-09-24
- Jev-as-a-Judge: hybrid agent eval flow escalates low-confidence calls to frontier models — omarsar0 · 2026-09-24