Code execution
Code execution with MCP: building more efficient AI agents \ Anthropic https://www.anthropic.com/engineering/code-execution-with-mcp
Similar idea.
Code execution with MCP enables agents to use context more efficiently by loading tools on demand, filtering data before it reaches the model, and executing complex logic in a single step. There are also security and state management benefits to using this approach.
LLMs are adept at writing code and developers should take advantage of this strength to build agents that interact with MCP servers more efficiently.
// So anthropic is a company that really focus on coding capabilities and use code as building blocks for intelligence.
// My idea is more extreme, treat llm as a compiler.