Fastest enterprise AI gateway (50x faster than LiteLLM) with adaptive load balancer, cluster mode, guardrails, 1000+ models support & <100 ยตs overhead at 5k RPS.
Add to ~/Library/Application Support/Claude/claude_desktop_config.json
{
"mcpServers": {
"bifrost": {
"command": "npx",
"args": [
"-y",
"@modelcontextprotocol/server-bifrost"
]
}
}
}