Skip to main content

​
Overview

Connect CodeAlive with Cursor IDE to enhance your AI-powered development experience. CodeAlive provides Cursor with deep contextual understanding of your entire codebase through the Model Context Protocol (MCP).
Quick install: Run npx @codealive/installer to automatically configure CodeAlive for Cursor. See the Installation Guide for details.

​
Prerequisites

  • Cursor installed
  • CodeAlive account with API key (Sign up here)
  • Indexed repositories in your CodeAlive dashboard

​
Connecting to CodeAlive

1

Open Cursor Settings

Navigate to Cursor’s MCP settings:
  • macOS: Cmd+Shift+P → “MCP: Configure Servers”
  • Windows/Linux: Ctrl+Shift+P → “MCP: Configure Servers”
  • Or navigate through: Settings → Features → MCP
2

Add CodeAlive Server

Cursor supports MCP with elicitation and resources:Option 1: Project-specific (.cursor/mcp.json):
{
  "servers": {
    "codealive": {
      "type": "http",
      "url": "https://mcp.codealive.ai/api/",
      "headers": {
        "Authorization": "Bearer ${CODEALIVE_API_KEY}"
      }
    }
  }
}
Option 2: Global (~/.cursor/mcp.json):
{
  "servers": {
    "codealive": {
      "type": "http",
      "url": "https://mcp.codealive.ai/api/",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY_HERE"
      }
    }
  }
}
Cursor’s Composer Agent automatically uses MCP tools when relevant
Replace YOUR_API_KEY_HERE with your actual CodeAlive API key
3

Reload Cursor

Reload the Cursor window for changes to take effect:
  • All platforms: Cmd/Ctrl+R or “Developer: Reload Window”
4

Verify Integration

Test in Cursor’s AI chat:
  • “What repositories are available in CodeAlive?”
  • “Search for authentication logic in my codebase”
  • “Explain the architecture of my project”

​
Cursor Rules Configuration

Create a .cursorrules file in your project root to optimize Cursor’s AI with CodeAlive: 
# CodeAlive-Enhanced Cursor Rules

## Context Awareness
- Always use CodeAlive to search for existing implementations before writing new code
- Reference actual code from the repository when explaining concepts
- Check for existing patterns and conventions in the codebase

## Code Generation
- Match the style and patterns found in the existing codebase
- Use CodeAlive to find similar code and follow those conventions
- Verify imports and dependencies exist in the project

## Code Review
- Search for related code that might be affected by changes
- Check for existing tests that need updates
- Look for similar implementations to ensure consistency

## Debugging
- Use CodeAlive to trace function calls and data flow
- Search for error handling patterns in the codebase
- Find related logs and debugging statements

​
Usage Patterns

Cursor AI: "Complete this function based on our codebase patterns"

// Cursor analyzes existing patterns via CodeAlive
// and suggests completions matching your style

​
Advanced Features

​
Multi-File Operations

Cursor can use CodeAlive to work across multiple files: 
"Show me all files that import UserService"
"Find all API endpoints that call this function"
"List database migrations related to users"

"What will break if I change this interface?"
"Find all tests affected by this change"
"Show usage of this deprecated method"

"Find similar error handling patterns"
"Show all authentication middleware"
"Locate all database transactions"

​
Workspace Configuration

​
Project-Specific Settings

Create .cursor/settings.json in your project: 
{
  "mcp.servers": {
    "codealive": {
      "type": "http",
      "url": "https://mcp.codealive.ai/api/",
      "headers": {
        "Authorization": "Bearer ${env:CODEALIVE_API_KEY}"
      },
      "repositories": ["repo-1", "repo-2"]
    }
  }
}

​
Team Collaboration

Share configuration with your team:
  1. Add to version control (without API keys)
  2. Team members set environment variable:
export CODEALIVE_API_KEY="their_api_key"

​
Docker Alternative

Run CodeAlive locally with Docker: 
docker run -d \
  -p 8000:8000 \
  -e CODEALIVE_API_KEY=YOUR_API_KEY \
  --name codealive-mcp \
  ghcr.io/codealive-ai/codealive-mcp:main
Then update Cursor configuration: 
{
  "servers": {
    "codealive": {
      "type": "http",
      "url": "http://localhost:8000/api",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

​
Productivity Tips

Quick Commands

Create custom Cursor commands for CodeAlive operations

Context Windows

Use CodeAlive for codebases exceeding context limits

Model Selection

Use GPT-4 for complex analysis, GPT-3.5 for quick searches

Team Standards

Document conventions in .cursorrules

​
Troubleshooting

Solutions:
  1. Check MCP server status in Cursor console
  2. Verify API key is correct and active
  3. Reload Cursor window (Cmd/Ctrl+R)
  4. Check network connectivity
Solutions:
  1. Ensure repositories are fully indexed
  2. Wait for indexing to complete
  3. Verify API key has repository access
  4. Check specific repository filters
Solutions:
  1. Use more specific queries
  2. Limit search to specific repositories
  3. Check indexing status in dashboard
  4. Consider Docker deployment
For more solutions, see the Troubleshooting Guide.