Mcp Llm Gateway

MCP LLM Gateway

MCP-compatible LLM gateway that proxies completion requests to downstream OpenAI-compatible providers.

[PyPI] [Python] [Ruff]

mcp-name: io.github.daedalus/mcp-llm-gateway

Install

pip install mcp-llm-gateway

Usage

Configuration

Set the following environment variables:

• DOWNSTREAM_URL: Base URL for the OpenAI-compatible downstream API (required)
• DEFAULT_MODEL: Default model to use for completions (required)
• MODEL_LIST_URL: URL to fetch available models from (optional, defaults to models.dev)
• API_KEY: Optional API key for downstream (passthrough)
• TIMEOUT: Request timeout in seconds (optional, default: 60)

MCP Server

Run the MCP server with stdio transport:

mcp-llm-gateway

MCP Tools

The server exposes the following tools:

• list_models(): List all available models from the remote endpoint
• complete(prompt, model, max_tokens, temperature): Send a completion request to the downstream LLM provider

MCP Resources

• models://list: Returns the list of available models
• config://info: Returns current gateway configuration

Development

git clone https://github.com/daedalus/mcp-llm-gateway.gitcd mcp-llm-gatewaypip install -e ".[test]"
# run testspytest
# formatruff format src/ tests/
# lintruff check src/ tests/
# type checkmypy src/

API

core.models

• Model: Dataclass representing an available LLM model
• CompletionRequest: Dataclass for completion request payloads
• GatewayConfig: Dataclass for gateway configuration

adapters.http

• HTTPAdapter: HTTP client for downstream API communication
• ModelListAdapter: Adapter for fetching model list from remote endpoints

services.gateway

• ModelService: Service for managing model discovery and caching
• CompletionService: Service for handling completion requests
• ConfigService: Service for managing gateway configuration