MCP By Design: The Protocol That Won't Be Patched
Anthropic markets MCP as the universal AI tooling standard, but a 200,000-server RCE class is 'expected behavior.' You can't be both.
Read more →
Posts related to mcp
7 posts
Anthropic markets MCP as the universal AI tooling standard, but a 200,000-server RCE class is 'expected behavior.' You can't be both.
Read more →Vercel got breached through Context.ai, an AI tool an employee installed with OAuth scopes into Google Workspace. It's the latest in a pattern: Trivy into litellm, axios maintainer hijack, now this. The safest AI tool is the one you didn't install.
Read more →Playwright MCP's 26 tools are killing your context window. Vercel's agent-browser shows a better way: fewer tools, smarter snapshots, 93% less overhead.
Read more →Task management designed for AI coding agents. CLI-first, git-native sync, and Model Context Protocol integration.
Read more →ENABLE_EXPERIMENTAL_MCP_CLI eliminates MCP tool schema overhead entirely. Undocumented, untested in the wild, but it works. Here's what I found.
Read more →Claude's new model ships with defer_loading for tools. The MCP isolation patterns I built are now (mostly) obsolete.
Read more →From Chrome DevTools experiment to universal MCP wrapper: progressive discovery works with any server, Skills integration, and smart deduplication
Read more →