一个轻量级、可配置的反向代理，用于路由和负载均衡MCP（模型上下文协议）请求，基于请求内容向相应后端服务进行路由和负载均衡。

如需详细文档，请访问Catie MCP文档。

特色

• 基于工具调用的 MCP JSON-RPC 请求动态路由
• 将多个不同MCP服务器的工具串接起来，使客户端无需安装多个服务器即可统一查看所有工具。
• 会话感知路由，以保持客户端连接到同一后端
• 支持通过SSE（服务器发送事件）进行可流式HTTP传输
• 工具名称映射和命名空间，以解决不同后端之间的命名冲突
• Prometheus指标集成以实现可观测性
• 使用 Docker 进行容器化部署
• 用于监控UI的基本认证

建筑

该应用程序结构化为几个包：

• cmd/main.go - 应用入口点带服务器设置
• pkg/config - 配置加载和管理
• pkg/router - 请求路由与代理逻辑
• pkg/session - 用于维护客户端连接的会话管理
• pkg/logger - 结构化日志系统

MCP Catie - Context Aware Traffic Ingress Engine

A lightweight, configurable reverse proxy for routing and load balancing MCP (Model Context Protocol) requests to appropriate backend services based on request content.

For detailed documentation, visit Catie MCP Documentation.

Features

• Dynamic routing of MCP JSON-RPC requests based on tool call
• Concatenate tools from multiple different MCP Servers so the client gets a unified view of all tools without the user installing multiple servers.
• Session-aware routing to maintain client connections to the same backend
• Support for Streamable HTTP transport with SSE (Server-Sent Events)
• Tool name mapping and namespacing to resolve naming conflicts between different backends
• Prometheus metrics integration for observability
• Containerized deployment with Docker
• Basic authentication for monitoring UI

Architecture

The application is structured into several packages:

• cmd/main.go - Application entry point with server setup
• pkg/config - Configuration loading and management
• pkg/router - Request routing and proxy logic
• pkg/session - Session management for maintaining client connections
• pkg/logger - Structured logging system
• pkg/ui - Simple web UI for monitoring

Configuration

The router is configured using a YAML file (router_config.yaml). Here’s an example configuration:

resources:
  "^weather/.*": "http://weather-service:8080/mcp"
  "^database/.*": "http://database-service:8080/mcp"
tools:
  "^calculator$": "http://calculator-service:8080/mcp"
  "^translator$": "http://translator-service:8080/mcp"
toolMappings:
  - originalName: "weather"
    targetName: "getWeather"
    target: "http://weather-service:8080/mcp"
  - originalName: "search"
    targetName: "googleSearch"
    target: "http://search-service:8080/mcp"
default: "http://default-service:8080/mcp"
ui:
  username: "admin"
  password: "your_secure_password"

The configuration consists of:

• resources: Regex patterns for resource URIs and their target endpoints
• tools: Regex patterns for tool names and their target endpoints
• toolMappings: Mappings for tool name transformations to resolve naming conflicts
• default: Fallback endpoint for requests that don’t match any pattern
• ui: Authentication credentials for the monitoring UI

The configuration file is automatically reloaded when changes are detected.

Tool Name Mapping

The tool name mapping feature allows you to present a unified tool interface to clients while handling naming differences across backend MCP servers. This is useful when:

• Different backends use different names for similar functionality
• You want to present a simplified or standardized naming scheme to clients
• You need to avoid naming conflicts between tools from different backends

For each tool mapping, specify:

• originalName: The name presented to clients