memento

Build, refactor, explain, or review Model Context Protocol (MCP) servers in Python using the official Python SDK and FastMCP. Use this whenever the user mentions Python MCP servers, FastMCP, MCP tools/resources/prompts, stdio transport, streamable HTTP transport, MCP server scaffolding, or converting a Python service into an MCP server, even if they do not explicitly say "use a skill."

Patterns and techniques for adding governance, safety, and trust controls to AI agent systems. Use this skill when: - Building AI agents that call external tools (APIs, databases, file systems) - Implementing policy-based access controls for agent tool usage - Adding semantic intent classification to detect dangerous prompts - Creating trust scoring systems for multi-agent workflows - Building audit trails for agent actions and decisions - Enforcing rate limits, content filters, or tool restrictions on agents - Working with any agent framework (PydanticAI, CrewAI, OpenAI Agents, LangChain, AutoGen)