Mcp Llm Gateway

io.github.daedalusPublished by GitHub account daedalusv0.1.0Updated Oct 24, 2026

MCP-compatible LLM gateway that proxies completion requests.

VerifiedSTDIODesktop onlyDeveloper Tools AI & ML

Server details

Identifier: io.github.daedalus/mcp-llm-gateway
Transport: STDIO
Runtime: Desktop only
Trust: Verified
Published: Sep 16, 2026

Security note

MCP servers receive tool arguments from a conversation and may perform external actions. Review what a server can do before you enable it, and give it only the access it needs.

The registry verified the GitHub account daedalus for this listing. That does not show the account is the product's maker.

SourceWeft's checks cover whether the listing is complete and the endpoint answered; they do not review the server's code or what its tools do.

Add a badge to your README

Show readers this MCP server is listed on SourceWeft. The badge links to this page.

[![Listed on SourceWeft](https://sourceweft.com/badge/mcp/io.github.daedalus%2Fmcp-llm-gateway.svg)](https://sourceweft.com/mcp/io.github.daedalus%2Fmcp-llm-gateway?utm_source=readme&utm_medium=badge)

Overview

AI-generated overview

A local MCP gateway that lets an assistant list models and send completion requests to an OpenAI-compatible LLM provider.

What you can do: List available models from the configured remote endpoint or the default model catalog, and read the same list as a resource. Send completion requests with a chosen model, max tokens and temperature to the downstream OpenAI-compatible provider. Read the current gateway configuration as a resource.
When to use it: Useful when you want an assistant to route completions through your own OpenAI-compatible endpoint or model gateway, or to compare or pick among models exposed by that endpoint.
Requirements: Runs as a local Python process installed from PyPI (pip install mcp-llm-gateway) over stdio. Requires the DOWNSTREAM_URL and DEFAULT_MODEL environment variables; MODEL_LIST_URL, API_KEY and TIMEOUT are optional. Network access to the downstream provider is needed.

Before you install

The API_KEY environment variable is passed through to the downstream provider, so treat it as a secret. Completion requests are sent to the configured downstream URL, so prompts leave your machine for that third party. The config://info resource exposes the current gateway configuration, which may include endpoint details.

Installation

In SourceWeft

Open Mcp Llm Gateway in the dashboard and add it to a workspace.
Enable the server for the chats that should use its tools.

Desktop only via STDIO. STDIO servers start a local process, so they need the SourceWeft desktop host.

Other MCP clients

Follow the launch instructions in the repository.

README

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

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 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

bash

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/

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

Source: README.md at commit eef35d0

Tools

SourceWeft has not started this package in its sandbox yet, so its tools are not known.

Version history

v0.1.0LatestSep 16, 2026

Score

50% of the applicable checks met

How complete this listing is, computed from the registry entry, the endpoint and public sources. Not a rating of the server and not a statement that it is safe or working today: reachability is a dated check, and no installs or reviews go into the score.

Reached in the last 30 days25 pts
Keep the endpoint answering the MCP handshake; SourceWeft probes it every 30 days.
Auth declared10 pts
Declare the credential headers in the registry entry, or keep the endpoint answering the probe so its auth can be classified.
Tools listed15 pts
Answer tools/list without a credential, or ship a package that starts in a sandbox without one.
DescriptionRequired15 pts
Logo10 pts
Documentation15 pts
License10 pts