MCP
13 mentions across all digests
MCP (Model Context Protocol) is an open standard for integrating external tools and capabilities into AI agents, used by agentic coding tools like Claude Code and embedded in AI IDEs such as Modo.
My minute-by-minute response to the LiteLLM malware attack
Forensic analysis of suspected LiteLLM supply chain attack reveals orphaned Python processes and base64-encoded payloads were actually normal Claude Code execution behavior, not malware.
AI supply chain attacks don’t even require malware…just post poisoned documentation
Security researcher Mickey Shmueli demonstrated that Context Hub's MCP service can be compromised through documentation poisoning, letting attackers inject arbitrary commands into coding agents like Claude Code without malware.
sem: Semantic version control CLI
Sem replaces line-by-line Git diffs with semantic entity-level change tracking via tree-sitter, letting AI agents reason about code changes at the abstraction level developers actually work with.
Show HN: Modo – I built an open-source alternative to Kiro, Cursor, and Windsurf
Open-source IDE Modo replicates commercial AI editors' core features (chat, inline editing, autocomplete) on the Void editor with multi-provider LLM support, suggesting the rapid AI IDE market has room for lightweight open alternatives.
EP209: 12 Claude Code Features Every Engineer Should Know
ByteByteGo maps 12 essential Claude Code features—from Plan Mode to MCP integrations—that establish a foundation for agentic engineering workflows.