Claude Code 2.1.327 lets you add MCP servers from stdin to keep tokens off the command line. It also expands /status diagnostics and fixes bugs that deleted .mcp.json keys and git-ignored files.
Key takeaways · AI-distilled
Claude Code 2.1.327 adds claude MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition → add-json <name> - to read a server's JSON from stdin so tokens stay off the command line, and a /status list of broken AI agentAn AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.Full definition →, agent skillA reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.Full definition → and command files, ignored permission settings and agent hookA script the harness runs automatically at a fixed point in an agent's loop — before a tool call, after an edit, on session start.Full definition → matchers that never match.
It fixes Remote Control's worktree mode deleting a running session's git-ignored files such as .env when the server stops, and claude mcp add/remove with project scope wiping other top-level keys from .mcp.json.
Auto mode now ignores more allow rules that can run any package, such as Bash(pnpm dlx *), leaving them to its safety check, and its notice says an upcoming release removes the fallback to billed classifier requests.
Remote MCP servers reached by hostname over https are now retried in the background for about a day after an outage such as a VPN drop, and WebFetch refuses URLs over 2,000 characters before any permission prompt.
A session's first Bash command starts faster because shell start-up files may now run before the command is approved, even if it is then refused; CLAUDE_CODE_DISABLE_SHELL_HEAD_START=1 turns this off.
Terms in this piece · Glossary
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
agent skill — A reusable instruction file that teaches an agent how to do one job well — the procedure, the tools, and what counts as done.
agent hook — A script the harness runs automatically at a fixed point in an agent's loop — before a tool call, after an edit, on session start.