MCP servers

maximhq/bifrost

Open-source, high-performance AI gateway that works as your LLM gateway, MCP gateway and agent gateway. One OpenAI-compatible API for 10,000+ models, with failover, load balancing, semantic caching, virtual keys, budgets and MCP Code Mode. Works with any SDK or agent and adds under 200µs of overhead at 5k RPS.

Stars
9,944
+7 days
—
Forks
1,647
Language
Go
License
Apache-2.0
Last push
22 Nov 2026

Summary

Summary written by AI from the README; it may be imprecise.

This open-source AI gateway provides a unified OpenAI-compatible API to connect with more than 23 model providers such as OpenAI, Anthropic, and AWS Bedrock. It handles automatic failover, load balancing, semantic caching, budget tracking, and Model Context Protocol (MCP) tooling. Developers can run it via NPX, Docker, or embed it using the Go SDK.

Use it when

  • When routing requests across multiple LLM providers through a single unified API endpoint
  • When needing automatic failovers, key load balancing, and semantic caching to reduce costs and downtime
  • When connecting external tools to AI agents using Model Context Protocol (MCP)

Install

npm
npx -y @maximhq/bifrost

Commands quoted from the repo's README. Read the README before running them.

Stars over 90 days

Collecting: 2 of 90 days so far. The chart appears after 7 days.

Type to search the reference, templates and lessons.