Integrations
MCP Server
Let AI assistants analyze videos directly through Claude, Cursor, or Windsurf.
The NetraFlow MCP server lets AI assistants submit and retrieve video analyses directly. No SDK installation required — it runs via npx.
Prerequisites
- Node.js 22+
- A NetraFlow API key
IDE configuration
Add to ~/Library/Application Support/Claude/claude_desktop_config.json (macOS) or %APPDATA%\Claude\claude_desktop_config.json (Windows):
{
"mcpServers": {
"netraflow": {
"command": "npx",
"args": ["-y", "@netraflow/mcp-server"],
"env": {
"NETRAFLOW_API_KEY": "sk_live_your_key_here"
}
}
}
}Add to .cursor/mcp.json in your project root:
{
"mcpServers": {
"netraflow": {
"command": "npx",
"args": ["-y", "@netraflow/mcp-server"],
"env": {
"NETRAFLOW_API_KEY": "sk_live_your_key_here"
}
}
}
}Add to ~/.codeium/windsurf/mcp_config.json:
{
"mcpServers": {
"netraflow": {
"command": "npx",
"args": ["-y", "@netraflow/mcp-server"],
"env": {
"NETRAFLOW_API_KEY": "sk_live_your_key_here"
}
}
}
}Available tools
Prop
Type
Environment variables
Prop
Type