A developer measured the token overhead of the Model Context Protocol (MCP) and found that loading 255 tools from 50 MCP servers consumes 71,929 tokens per session, compared to just 123 tokens for the…
AI agent tool calling has converged on open protocols like MCP, function calling, and A2A, but scaling to multi-user production agents introduces new bottlenecks in tool quality, context efficiency, m…
Scalekit ran 75 benchmark runs comparing CLI and MCP agents on identical GitHub tasks, finding CLI was 10 to 32x cheaper and 100% reliable, while MCP hit only 72% reliability. Perplexity's CTO reporte…
Google announced that WebMCP, a new standard proposal enabling websites to expose tools to in-browser AI agents, is entering origin trials in Chrome 149. The protocol allows AI agents to reliably simu…