Search documentation
Search pages, API reference sections, and guide headings.
Summary
Claude Desktop uses the stdio transport. The public helper endpoint `/mcp/config` generates the same `mcpServers` JSON shape documented here.
Install or run with npx
Claude Desktop can launch the server with npx, so a global install is optional.
{
"mcpServers": {
"videosearch": {
"command": "npx",
"args": ["@videosearch/mcp-server"],
"env": {
"VIDEOSEARCH_API_KEY": "sk_live_..."
}
}
}
}
Config path
The helper controller returns this default config path for macOS:
~/Library/Application Support/Claude/claude_desktop_config.json
The setup instructions embedded in the controller also document the Windows equivalent.
Verification
After saving the config and restarting Claude Desktop, verify the connection by asking Claude which VideoVector tools are available.
Generated config endpoint
Use the helper endpoint when you want a platform-specific config payload:
curl "/api/v2/mcp/config?platform=claude-desktop" \
-H "Authorization: Bearer <verified-jwt>"
If you omit api_key_id, the server will reuse a suitable key or create a new one with read and search scopes.
Related documentation
This guide connects AI clients to VideoVector tools for media retrieval, prompt execution, workflow inspection, and playground validation.
Custom clients can use the same stdio server config as Claude Desktop and Cursor or connect to a remote HTTP deployment when the MCP server must be network addressable.
The public MCP helper endpoints expose tool definitions, category groupings, platform-specific configs, and direct playground execution so you can validate integrations before deploying them.
