AmoyLab/Unla

🧩 MCP Gateway - A lightweight gateway service that instantly transforms existing MCP Servers and APIs into MCP servers with zero code changes. Features Docker deployment and management UI, requiring no infrastructure modifications.

What it solves

Unla is a gateway service that allows users to turn existing APIs and MCP servers into Model Context Protocol (MCP) compliant endpoints. It eliminates the need to rewrite existing code to make legacy systems compatible with the MCP standard, allowing AI clients to interact with them seamlessly.

How it works

Written in Go, Unla acts as a proxy layer. It uses YAML configurations to map existing RESTful APIs or other MCP services to the MCP protocol. It supports multiple transport methods, including SSE (Server-Sent Events) and Streamable HTTP, and can be deployed via Docker, Kubernetes, or on bare metal.

Who it’s for

Developers and organizations who have existing API infrastructure and want to integrate their services with MCP-compatible AI agents and clients without modifying their original source code.

Highlights

  • Zero Code Changes: Converts APIs to MCP servers using configuration files rather than programming.
  • Management UI: Includes a built-in web interface for easy setup and server management.
  • Protocol Support: Supports MCP SSE and Streamable HTTP, handling text, image, and audio responses.
  • Enterprise Ready: Features multi-tenant support, persistent sessions, and deployment options for Kubernetes and Helm.
  • Flexible Configuration: Supports hot-reloading and persistence via SQLite, PostgreSQL, or MySQL.

Related

  • Project
    aklivity/zilla

    A stateless, multi-protocol gateway that provides a unified endpoint for AI agents and applications to access event streams (Kafka/MQTT) and federated MCP toolsets.

  • Project
    yym68686/uni-api

    uni‑api is a config‑only server that presents a single OpenAI‑compatible API while routing calls to many LLM providers (OpenAI, Anthropic, Gemini, Vertex, Azure, AWS, etc.). It supports weighted and round‑robin load balancing, automatic retries, per‑model timeouts, rate limits, tool‑call passthrough, content moderation, and fine‑grained request overrides—all defined in an `api.yaml` file or via a `CONFIG_URL`. Deployable as a Docker container (one‑click Fugue button provided).

  • Project
    mark3labs/mcp-go

    A Go implementation of the Model Context Protocol (MCP) that enables LLM applications to integrate with external data sources and tools using a standardized interface.

  • Project
    mattt/emcee

    A tool that converts any web application with an OpenAPI specification into a Model Context Protocol (MCP) server, allowing AI models to use the API as a tool.

  • Project
    ThinkInAIXYZ/go-mcp

    A Go implementation of the Model Context Protocol (MCP) SDK that enables seamless communication between external systems and AI applications.