CMMV FAQs

Question 1

What is CMMV's MCP module?

Accepted Answer

The `@cmmv/mcp` module implements the Model Context Protocol (MCP) for CMMV applications, enabling standardized communication between applications and Large Language Models (LLMs). It provides a structured interface for LLMs to call tools within your application.

Question 2

How do I define tools for LLMs to use with CMMV's MCP?

Accepted Answer

You define tools using the `@MCPTool` decorator. This decorator registers a method as an MCP tool, allowing you to specify a name and validation schema (using Zod) for the tool's input parameters.

Question 3

Why use Zod for schema validation in CMMV's MCP?

Accepted Answer

Zod ensures that the input parameters passed to your tools from the LLM adhere to a predefined schema. This helps prevent errors, improves code reliability, and ensures that your tool receives the expected data types.

Question 4

What are the key features of the MCP module?

Accepted Answer

Key features include bidirectional communication with LLMs, flexible transport options (SSE or Standard I/O), API decorator-based tool registration (@MCPTool), Zod validation for input schemas, and robust connection management for multiple concurrent connections.

Question 5

What transport methods does CMMV's MCP support?

Accepted Answer

The MCP module supports transport via Server-Sent Events (SSE) or Standard I/O, providing flexibility in how your application communicates with LLMs.

CMMV

About

Key Features