mcp-code-executionlisted

# MCP Code Execution Pattern Expert knowledge for designing agent systems that generate and execute code to interact with MCP servers, instead of calling tools directly. ## When to Use This Skill | Use this skill when... | Use mcp-management instead when... | |---|---| | Designing agents that fan out across 10+ MCP servers or 50+ tools | Installing or configuring a single MCP server in `.mcp.json` | | Intermediate tool results are large (>10K tokens) and would blow context | Operating one or two servers where every result is small enough to inline | | Workflows need loops, retries, or conditionals across tool calls | Doing a one-shot connection check or linear 2–3-call sequence | | PII must not reach the model context | Tool responses contain no sensitive data | ## When to Use This Pattern | Use code execution when... | Use direct tool calls when... | |----------------------------|-------------------------------| | Connecting to 10+ MCP servers or 50+ tools | Few servers with handful of tools | | Intermediate results are large (>10K tokens) | Results are small and all needed by the model | | Workflows need loops, retries, or conditionals | Linear sequences of 2-3 tool calls | | PII must not reach the model context | No sensitive data in tool responses | | Tasks benefit from state persistence across runs | Stateless, one-shot operations | | You want agents to accumulate reusable skills | Fixed, predefined workflows | ## Core Architecture ### How It Works Instead of loa