Cursor Integration

Connect your Vectorize MCP agent to Cursor for AI-powered coding with access to your documentation and knowledge base.

Prerequisites

• Cursor installed (Download here)
• MCP agent created in Vectorize
• At least one function configured
• API key generated for your agent

Quick Setup

1. Get Your Credentials

1. Open your MCP agent in Vectorize
2. Go to Agent API Keys
3. Click Create New Key and name it (e.g., "Cursor")
4. Save your API key securely
5. Note your Agent ID from the agent overview

2. Configure Cursor

1. Open Cursor Settings → MCP configuration

2. Add this configuration:

{
  "mcpServers": {
    "vectorize-mcp": {
      "url": "https://agents.vectorize.io/api/agents/YOUR_AGENT_ID/mcp",
      "headers": {
        "Authorization": "Bearer YOUR_API_KEY"
      }
    }
  }
}

3. Replace YOUR_AGENT_ID and YOUR_API_KEY with your actual values

Verify Connection

After configuration:

• Your agent appears in Cursor's MCP server list
• Functions are available for AI assistance
• Click function names to enable/disable them

Usage Tips

Effective Use Cases

• Code Documentation: "What does our authentication system do?"
• API Reference: "Show me examples of using our payment API"
• Best Practices: "What are our coding standards for React components?"
• Architecture: "Explain our microservices architecture"

Tips for Better Results

• Write clear function descriptions in Vectorize
• Use specific keywords from your documentation
• Test functions in Vectorize UI first
• Keep pipelines updated with latest docs

Troubleshooting

Agent Not Appearing

• Verify configuration format is correct
• Check API key and Agent ID
• Restart Cursor after configuration

No Results

• Ensure pipeline has indexed documents
• Check function filters aren't too restrictive
• Test queries in Vectorize UI

Authentication Errors

• Validate API key hasn't expired
• Confirm correct Agent ID
• Check network connectivity

Next Steps

• Configure more functions
• Optimize your pipelines
• View other integrations