mcp-server-design
MCP Server Design
MCP (Model Context Protocol) is a standard for connecting AI agents to external data and tools. An MCP server exposes tools, resources, and prompts that any MCP-compatible client (Claude Code, Claude Desktop, custom agent apps) can discover and use. Think of it as an API specifically designed for LLM consumption.
The design principle: an MCP server wraps an existing system (CRM, enrichment provider, sequencing tool, database) and presents it to the model in a way that's easy to understand and safe to use. The server handles authentication, rate limiting, data formatting, and access control. The model handles reasoning.
When to Build an MCP Server vs Use Direct Tool Calls
| Scenario | MCP server | Direct tool in agent code |
|---|---|---|
| Tool should be reusable across multiple agents | MCP server | Overkill |
| Tool is specific to one agent and won't be reused | Overkill | Direct tool |
| Multiple team members need access to the same data source | MCP server | Creates duplication |
| Tool requires complex auth (OAuth, API keys, session management) | MCP server (handles auth once) | Each agent reimplements auth |
| You want Claude Code or Claude Desktop to use the tool interactively | MCP server (required) | Not supported |
| Tool is a simple function with no external dependencies | Overkill | Direct tool |
Rule of thumb: If more than one agent or more than one person needs access to the same external system, build an MCP server. If it's a one-off utility function for a single agent, use a direct tool.