Handit.AI
  • Introduction
    • Introduction
    • Quick Start
  • Agent Creation
    • Overview
    • Interactive Agent Setup
    • Define Your Agent with a JSON Configuration
  • Code Integration
    • Overview
    • MCP Server Setup
    • Context Based Setup
    • Manual Setup
  • Best Practices
    • Input/Output Tracking
    • Service Initialization
    • Error Handling
Powered by GitBook
On this page
  • Quick Start: Enable the MCP Server
  • Connecting Your Code
  • Next Steps
  1. Code Integration

MCP Server Setup

PreviousOverviewNextContext Based Setup

Last updated 1 month ago

The MCP (Model Context Protocol) server acts as the bridge between Handit.AI and your local codebase when working in Cursor. This guide will walk you through enabling the server and connecting your code automatically—no manual instrumentation needed.

Quick Start: Enable the MCP Server

First, you’ll enable the MCP server inside your project. Cursor will then detect it automatically and make the Handit tools available within the editor.

  1. Download the MCP server zip file from your Handit.AI dashboard

  2. Extract the zip file to your project directory

  3. Open Cursor Settings

  4. Go to Features > MCP

  5. The MCP server will be automatically detected and listed

  6. Click the enable button to load the available tools

Connecting Your Code

Once the MCP server is running and detected by Cursor, you can use the AI assistant to auto-configure your code for monitoring and tracing.

In Cursor, type:

configure Handit on my agent on these files ... based on the MCP handit://context

The AI will analyze your codebase and automatically:

  • Configure the necessary Handit.AI client

  • Set up the appropriate tracking points

  • Connect your code to the MCP context

  • Generate the required configuration files

This eliminates the need for manual setup and ensures your code is ready to be monitored by Handit.AI immediately.

Next Steps

- Learn about best practices for using Handit.AI

Best Practices Guide