MCP Server

The Model Context Protocol (MCP) server enables you to expose your tools and resources to AI models, facilitating seamless integration and context-aware interactions.

To use the MCP Server, you will need an API Key. Learn how to generate one in the First Steps: API Keys guide.

What is MCP?

The Model Context Protocol (MCP) is an open standard that lets AI models discover and call external tools in a structured way. Instead of hardcoding API calls into your prompts, you register an MCP server and the model handles tool selection and invocation automatically.

Makinari’s MCP server exposes over 30 tools covering messaging, lead management, content, campaigns, reports, and more.

How it works

1. You connect the Makinari MCP server to your AI client (Claude Desktop, a custom agent, etc.).
2. The model sees a list of available tools with their descriptions and parameters.
3. When the model decides a tool is relevant, it calls it. The server executes the action against your Makinari project and returns the result.
4. The model uses the result to continue reasoning or respond to the user.

Setup options

• Remote (REST endpoints) - Connect to the hosted instance managed by Makinari. Fastest way to get started.
• Local installation - Run the server on your own machine for development or custom deployments.

Documentation

• Setup - Learn how to install and configure the MCP server.
• Tools - Explore the list of available tools exposed by the server.