Model Context Protocol · access layer
One secure endpoint for every MCP server your team trusts.
Bifrost sits between your AI tooling and a fleet of MCP servers — a single base URL to mount, keys you can scope and rotate, and a live audit log of every invocation, entirely on your own infrastructure.
port: 8787
baseUrl: https://mcp.example.com
servers:
github:
url: http://10.0.4.21:3001
postgres:
url: http://10.0.4.22:3002
keys: rotate: 30d · scopes: tools, prompts
How it works
Three moves. One endpoint.
Point one client at Bifrost
Add a single entry to your client config pointing at your gateway base URL.
"mcpServers": {
"bifrost": {
"url": "https://mcp.example.com",
"headers": {
"Authorization": "Bearer sk_live…"
}
}
}
}
Attach the servers you need
Register any MCP server — internal or external — and let Bifrost resolve and proxy by tool name.
Issue keys, then watch it work
Scope keys per tool or team, rotate them on a schedule, and audit every call from your own dashboard.
What's different
The access layer your fleet has been missing.
Mount once, route by tool
Point your client at one base URL. Bifrost resolves each tool call to the right server and proxies it — no per-server credentials tangled across your config.
Keys you can scope and rotate
Issue API keys per tool, per team, or per project. Revoke one without rebuilding the fleet — and know exactly who called what, and when.
tools:githubtools:postgresrevokedObservability built in
Every invocation lands in a searchable trace — latency, payload size, status. You see the whole fleet's activity in one pane, without bolting on a stack.
Stop duplicating keys. Mount one gateway.
Runs on your infrastructure — your keys, your network, your audit trail. Docker up in five minutes.
Read the docs