Code execution with MCP: Building more efficient agents
Source
Anthropic
Author
Anthropic
Date
Terms in this piece · Glossary
MCP — The Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.
token — The chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.
context window — The maximum amount of text a model can consider at once — its working memory for the current conversation or task.
Why it matters
It shows how to slash tokenThe chunk of text a model reads and writes in — roughly three-quarters of a word — and the unit AI usage is billed in.Full definition → overhead and improve reliability in MCPThe Model Context Protocol — an open standard that lets any AI assistant plug into any tool or data source without custom integration code.Full definition →-based agents by having them generate and execute code against tool APIs instead of loading every tool definition into context windowThe maximum amount of text a model can consider at once — its working memory for the current conversation or task.Full definition → — a pattern that scales to hundreds of tools where naive tool-calling breaks down.
Key quotes
“Today developers routinely build agents with access to hundreds or thousands of tools across dozens of MCP servers. However, as the number of connected tools grows, loading all tool definitions upfront and passing intermediate results through the context window slows down agents and increases costs.”
Anthropic
“Every intermediate result must pass through the model. In this example, the full call transcript flows through twice. For a 2-hour sales meeting, that could mean processing an additional 50,000 tokens. Even larger documents may exceed context window limits, breaking the workflow.”
Anthropic
“This lets the agent load only the definitions it needs for the current task. This reduces the token usage from 150,000 tokens to 2,000 tokens—a time and cost saving of 98.7%”
Anthropic
“When agents use code execution with MCP, intermediate results stay in the execution environment by default. This way, the agent only sees what you explicitly log or return, meaning data you don’t wish to share with the model can flow through your workflow without ever entering the model's context.”
Anthropic
“Note that code execution introduces its own complexity. Running agent-generated code requires a secure execution environment with appropriate sandboxing , resource limits, and monitoring.”
