Add web search to Cursor's AI agent by configuring the Scavio MCP server. The background agent can then verify documentation, check API versions, and research solutions using live search data instead of stale training data.
Prerequisites
- Cursor IDE installed (Pro $20/mo recommended)
- Scavio API key from scavio.dev
- A project directory
Walkthrough
Step 1: Create MCP configuration
Create .cursor/mcp.json in your project root.
Bash
mkdir -p .cursor
cat > .cursor/mcp.json << 'EOF'
{
"mcpServers": {
"scavio": {
"url": "https://mcp.scavio.dev/mcp",
"headers": {
"Authorization": "Bearer YOUR_API_KEY"
}
}
}
}
EOFStep 2: Verify in Cursor settings
Open Cursor Settings > MCP to confirm the server is connected.
Bash
# In Cursor:
# 1. Open Settings (Cmd+,)
# 2. Navigate to MCP section
# 3. Verify 'scavio' server shows as connected
# 4. Test with: 'Search for Express.js rate limiting best practices'Python Example
Python
import json, os
# Create .cursor directory and MCP config
os.makedirs('.cursor', exist_ok=True)
config = {
'mcpServers': {
'scavio': {
'url': 'https://mcp.scavio.dev/mcp',
'headers': {
'Authorization': 'Bearer YOUR_API_KEY'
}
}
}
}
with open('.cursor/mcp.json', 'w') as f:
json.dump(config, f, indent=2)
print('MCP search configured for Cursor')JavaScript Example
JavaScript
const fs = require('fs');
fs.mkdirSync('.cursor', {recursive: true});
const config = {
mcpServers: {
scavio: {
url: 'https://mcp.scavio.dev/mcp',
headers: {Authorization: 'Bearer YOUR_API_KEY'}
}
}
};
fs.writeFileSync('.cursor/mcp.json', JSON.stringify(config, null, 2));
console.log('MCP search configured for Cursor');Expected Output
JSON
Cursor IDE with live search capability. The background agent verifies documentation and API versions before writing code.