MCP has outputSchema so agents can validate tool results. But does the schema actually reject a wrong...
I tested 31 MCP servers for contract compliance. Only 3% passed.
Related
I stopped babysitting Claude Code: spec in, pull request out
I use Claude Code on real repos every day, often in two or three sessions at once. The code was...
What a device tool costs your coding agent: a React Native benchmark
I gave Claude Code five bugs that only show up in a running React Native app. We asked it to find the...
38,000 AI-found vulnerabilities, 217 fixed: auditing Glasswing, Anthropic's bug-discovery machine
Seven months ago Anthropic claimed thousands of high-severity AI-discovered bugs. The independent audit is in: 37,966 findings, 7,349 public, 217 fixed, and an October scanner that...