Log inSubmit server
Bifrost logo

Bifrost

Routes AI requests across multiple model providers and exposes MCP-based access to external tools through one gateway.

InstallRepositoryWebsite
Full README Compare alternatives Embed widget Claim this listing

Install Bifrost

Pick your client, then add it in one click or paste the config.

No confirmed install command yet

We only publish a config when the install details come from the project itself — its README, its docs, or a verified owner. We haven’t found those for bifrost, and we’d rather show nothing than a guess you’d paste into your client.

Open setup steps on GitHub

Overview

bifrost MCP server provides an AI gateway with a unified OpenAI-compatible API across 23+ providers, including OpenAI, Anthropic, AWS Bedrock, and Google Vertex. Its MCP gateway capability lets AI models use external tools such as filesystem access, web search, and databases. The gateway also supports failover, load balancing, semantic caching, governance, and observability. Reach for bifrost when applications need one operational layer for multiple model providers and MCP-enabled workflows.

Use cases

  • Route model traffic across multiple providers
  • Expose external tools to AI models through an MCP gateway
  • Add failover and load balancing to AI applications
  • Centralize budgets, access controls, and usage tracking
  • Monitor model requests with metrics and tracing

Key features

  • OpenAI-compatible multi-provider API
  • MCP gateway for external tools
  • Automatic failover and load balancing
  • Semantic response caching
  • Budgets, virtual keys, and access controls
  • Prometheus metrics and distributed tracing

Security & health

What it can reach and how reliably it runs — from our own checks, not the maintainer’s claims.

ActiveLast checked Today

Recent health check succeeded.

Adoption & maintenance

Factual signals from GitHub, npm, and our automated checks — not a rating.

GitHub stars9.4kStargazers on the source repository.
Last commitTodayMost recent push to the default branch.

How Bifrost works

What bifrost does

bifrost combines model routing and MCP gateway functions in a single AI infrastructure layer. Applications can send requests through one OpenAI-compatible API while bifrost manages connections to more than 23 model providers, including OpenAI, Anthropic, AWS Bedrock, Google Vertex, Azure, Cerebras, Cohere, Mistral, Ollama, and Groq.

Its MCP capability allows AI models to use external tools, with the project identifying filesystem operations, web search, and databases as examples. The wider gateway also covers request reliability, cost controls, access management, and operational visibility.

How it works

The gateway accepts HTTP requests using familiar OpenAI-compatible routes, such as /v1/chat/completions, and uses the requested model identifier to route traffic to a configured provider. Multiple providers or API keys can be used for automatic fallback and load distribution. Semantic caching can reuse responses for semantically similar requests, reducing repeated work and latency.

A built-in web interface provides configuration, monitoring, and analytics. Configuration can also be managed through the API or files. For Go applications, the project offers a core SDK that can be embedded directly instead of running the HTTP gateway as a separate service.

MCP gateway support is described as an enterprise capability. This makes bifrost relevant to deployments that need centralized control over model access and external tool use, rather than only a local, standalone MCP process.

Setup and configuration

The gateway can be started locally with NPX:

Terminal
npx -y @maximhq/bifrost

Docker is also supported:

Terminal
docker run -p 8080:8080 maximhq/bifrost

After startup, open http://localhost:8080 to use the web interface. The gateway can then be called over HTTP on port 8080. A persistent data directory can be mounted for Docker deployments:

Terminal
docker run -p 8080:8080 -v $(pwd)/data:/app/data maximhq/bifrost

Provider configuration is available through the web UI, API, or configuration files. Secrets can be supplied through environment variables and deployment secrets.

Tools and capabilities

  • Route requests through a common OpenAI-compatible API.
  • Connect applications to multiple model providers.
  • Fail over between providers and models.
  • Balance traffic across providers and API keys.
  • Let models use external MCP tools such as filesystem, web search, and database tools.
  • Apply semantic caching, budgets, rate limits, and virtual-key access controls.
  • Expose Prometheus metrics, distributed tracing, logging, and analytics.

Limitations and notes

The project presents MCP gateway functionality as part of its enterprise deployment capabilities. The documented quick start focuses on the general HTTP gateway and provider routing, not on a standalone local MCP server configuration. Provider availability, governance features, and MCP gateway access may therefore depend on the deployment edition and configuration.

Read the full README View source on GitHub

Reviews

No reviews yet — be the first to share how it worked for you.

Frequently Asked Questions about Bifrost

bifrost is an MCP server that connects AI models and applications to external tools such as filesystem access, web search, and databases through an MCP gateway. It also routes model requests across 23+ providers using one OpenAI-compatible API, with failover, load balancing, caching, governance, and observability features.

Install the bifrost gateway with NPX using `npx -y @maximhq/bifrost`, or run the `maximhq/bifrost` Docker image with port 8080 exposed. Then open `http://localhost:8080` to configure the gateway through its web interface.

Yes, bifrost provides one OpenAI-compatible API for more than 23 providers, including OpenAI, Anthropic, AWS Bedrock, Google Vertex, Azure, Cerebras, Cohere, Mistral, Ollama, and Groq. It can also fail over between providers and distribute traffic across keys and providers.

Yes, bifrost includes an MCP gateway capability for enabling models to use external tools. The project lists filesystem access, web search, and databases as example tool categories, and identifies MCP gateway functionality among its enterprise deployment features.

Yes, bifrost provides a Go SDK through the `github.com/maximhq/bifrost/core` package. The SDK supports direct Go integration, embedded deployment, and custom middleware integration without requiring the HTTP gateway as a separate service.

Related MCP servers

All in Aggregators All alternatives
Add a badge to your READMEShow it’s listed — live SVG, Markdown or HTML.

AllMCPs Directory Badge

Full Badge Customizer

Showcase your server listing on GitHub or your project documentation. Embed this dynamic SVG badge to highlight official listing status and live engagement.

Badge Style:
Live Dynamic SVG PreviewBifrost AllMCPs Directory Badge
Markdown (GitHub README)
[![AllMCPs](https://allmcps.com/api/badge/bifrost?style=directory)](https://allmcps.com/mcp/bifrost)
HTML Embed
<a href="https://allmcps.com/mcp/bifrost"><img src="https://allmcps.com/api/badge/bifrost?style=directory" alt="Bifrost on AllMCPs" /></a>