AINewsnow

readOnlyHint isn't a permission: blocking a destructive MCP tool by policy

This story is from 2026-10-27. It is preserved in the archive; the latest stories are on the live feed.

MCP lets a tool describe itself. readOnlyHint: true says "I only read". destructiveHint: true says "I can delete or overwrite something". Clients can use those hints to decide when to ask a person before running a tool. Two things go wrong with that in practice. The hint is often missing. We looked…

Read the full story at DEV Community — AI ↗

Timeline · 1 report

  1. 2026-10-27 10:53 · DEV Community — AI
    readOnlyHint isn't a permission: blocking a destructive MCP tool by policy

More stories

  1. Introducing GPT-6.1 Terra — OpenAI News
  2. Meta announces $95B offering to fund AI — Semafor Technology
  3. Microsoft offers buyouts to 60,000 employees — The Verge AI
  4. OpenAI announces three big science discoveries and a new way to work with academics — The Verge AI
  5. Anthropic’s IPO filing lays out a plan to ‘revolutionize every area of human endeavor' with AI — The Verge AI
  6. Anthropic's IPO filing shows soaring sales and steep losses — France 24 — Artificial Intelligence
  7. Apple unveils the 14-inch MacBook Pro with M6, with a 12-core CPU and a 12-core GPU, up to 32GB of unified memory, and Wi-Fi 7, from $1,999 on November 6 (Apple) — Techmeme
  8. Cohere says Alibaba’s Qwen model tried to send a file to Beijing — TechCrunch AI

Get the daily brief of stories like this at 6:30 every morning →