[ PERFORMANCE AT A GLANCE ]
[ ARCHITECTURE ]
Bifrost acts as both an MCP client (connecting to external tool servers) and an MCP server (exposing tools to external clients like Claude Desktop) through a single deployment.
Bifrost connects to your external MCP servers - filesystem tools, web search, databases, custom APIs, and discovers their capabilities automatically.
Bifrost exposes all connected tools through a single gateway URL. MCP clients like Claude Desktop connect to Bifrost and access everything.
[ CORE CAPABILITIES ]
Connect, secure, filter, and execute tools with explicit approval workflows, autonomous agent mode, and Code Mode for high-efficiency orchestration.
Connect to any MCP-compliant server via STDIO, HTTP, or SSE. Bifrost auto-discovers tools and their schemas at runtime so your AI models can use them immediately.
STDIO + HTTP + SSESecure OAuth 2.0 authentication with automatic token refresh
OAuth 2.0 with automatic token refreshTool calls from LLMs are suggestions only. Execution requires a separate API call, giving your app full control to validate, filter, and approve every action before it runs.
Security-firstEnable autonomous multi-step tool execution with configurable auto-approval. Specify exactly which tools can auto-execute while keeping human oversight for sensitive operations.
Configurable auto-approvalAI writes Python to orchestrate multiple tools. Four meta-tools replace 100+ definitions with on-demand schema loading and sandbox execution. Cuts tokens by 50%+ and LLM calls by 3-4x.
Token efficiencyA single endpoint for tool discovery, execution, and management.
Single gateway URL[ HOW IT WORKS ]
The default tool calling pattern is stateless with explicit execution. No unintended API calls, no accidental data modifications, full audit trail of every operation.
Connect Bifrost to any MCP-compliant server. Bifrost auto-discovers available tools and their schemas at startup.
Your app sends a standard chat completion request. Bifrost injects discovered MCP tools into the request automatically.
When the LLM suggests a tool call, your app decides whether to execute it. Bifrost handles the MCP protocol and returns results.
[ CODE MODE ]
If you're using 3+ MCP servers, classic tool calling becomes expensive. Every request sends all tool schemas to the LLM, burning tokens on definitions instead of work.
Code Mode takes a different approach: instead of exposing 100+ tool definitions, the AI writes Python code to orchestrate tools in a sandboxed environment. One round-trip handles what would take multiple sequential tool calls.
[ SECURITY-FIRST DESIGN ]
By default, Bifrost does NOT automatically execute tool calls. All tool execution requires explicit API calls from your application, ensuring human oversight for every operation.
Tool calls from LLMs are suggestions only. Execution requires a separate API call from your application.
Filter tools per-request, per-client, or per-virtual-key. Blacklist dangerous tools globally.
Agent Mode with auto-execution must be explicitly configured. Specify exactly which tools are allowed.
Each API call is independent. Your app controls conversation state with full audit trails at every step.
[ COMPARISON ]
Standard MCP tool calling works, but it doesn't scale. Code Mode solves the hard problems.
| Dimension | Classic MCP | Bifrost Code Mode |
|---|---|---|
| Tool definition overhead | 100+ tool schemas sent every request | AI writes code to call tools |
| Token usage | High (all tool schemas in context) | 50%+ reduction |
| Execution latency | Multiple round-trips per tool | 40% faster execution |
| Multi-tool orchestration | Sequential tool calls only | Python orchestrates in one pass |
| Scalability with servers | Degrades with 3+ servers | Scales to any number |
| Error handling | LLM retries each tool call | Python try/catch in sandbox |
[ TRANSPORT PROTOCOLS ]
Local process execution via stdin/stdout.
Local toolsRemote MCP servers via HTTP requests.
MicroservicesPersistent streaming for real-time data.
Live data[ USE CASES ]
Connect AI coding agents to filesystem tools, databases, and deployment pipelines. Bifrost handles tool injection transparently with full audit trails for every operation.
Deploy in healthcare, finance, or government with explicit approval workflows, PII redaction, and tamper-evident audit logs for SOC 2 and HIPAA compliance.
Coordinate filesystem operations, database queries, and API calls in a single request using Code Mode. Reduce token waste and latency when using 3+ MCP servers.
Supervised infrastructure actions and deployments with role-based tool access. Only approved tools execute, with complete visibility into every automated step.
Manage tool access across teams with virtual keys and per-key tool filtering. Set different tool policies for development, staging, and production environments.
Expose your entire tool ecosystem through a single Bifrost gateway URL. Claude Desktop and other MCP clients connect once and discover all available tools automatically.
[ WHY BIFROST ]
11µs overhead at 5,000 requests per second
Stateless architecture with explicit approval
Code Mode: 50% fewer tokens, 40% faster execution
Dual role: MCP Client and MCP Server
Built-in OAuth 2.0 with automatic token refresh
Production-proven at millions of requests/day
Complete audit trails and OpenTelemetry export
Open source (Apache 2.0) with enterprise support
Go-native with zero Python GIL bottleneck
[ BIFROST FEATURES ]
Everything you need to run AI in production, from free open source to enterprise-grade features.
01 Model Catalog
Access 8+ providers and 1000+ AI models from multiple providers through a unified interface. Also support custom deployed models!
02 Budgeting
Set spending limits and track costs across teams, projects, and models.
03 Provider Fallback
Automatic failover between providers ensures 99.99% uptime for your applications.
04 MCP Gateway
Centralize all MCP tool connections, governance, security, and auth. Your AI can safely use MCP tools with centralized policy enforcement. Bye bye chaos!
05 Virtual Key Management
Create different virtual keys for different use-cases with independent budgets and access control.
06 Unified Interface
One consistent API for all providers. Switch models without changing code.
07 Drop-in Replacement
Replace your existing SDK with just one line change. Compatible with OpenAI, Anthropic, LiteLLM, Google Genai, Langchain and more.
08 Built-in Observability
Out-of-the-box OpenTelemetry support for observability. Built-in dashboard for quick glances without any complex setup.
09 Community Support
Active Discord community with responsive support and regular updates.
Change just one line of code. Works with OpenAI, Anthropic, Vercel AI SDK, LangChain, and more.