mcp-agent-patterns
Installation
SKILL.md
MCP Agent Patterns (Model Context Protocol)
Overview
The Model Context Protocol (MCP) provides a standardized way for AI agents to interact with external tools, data resources, and environments. This skill defines architectural patterns and implementation best practices for building, connecting, and optimizing MCP-based systems within the KILO-KIT ecosystem.
When To Use
- Implementing custom MCP servers or clients.
- Integrating external services (APIs, DBs, filesystems) as MCP servers.
- Optimizing context windows when dealing with large tool catalogs.
- Implementing real-time resource synchronization or complex multi-server orchestrations.
- Security-critical integrations requiring isolated execution environments.
Core MCP Concepts
- Tools: Executable functions exposed to the LLM.
- Resources: Data sources that can be read by the LLM (e.g., file contents, database records).
- Prompts: Reusable templates or workflows designed to be used by the LLM.
- Sampling: A protocol allowing an MCP server to request the host client to perform LLM inference on its behalf, enabling agentic tool behavior.