MCP LLM Gateway MCP Server

by daedalus Your server? Claim it

local only

MCP LLM Gateway runs on your own machine — the client starts it, so there is no endpoint to ping. 56 installs a week from pypi. Last commit 21 Apr 2026.

MCP-compatible LLM gateway that proxies completion requests.

Installs per day peak 14 · avg 8 · -14% w/w

a month agotoday

Installs / week

pypi · mcp-llm-gateway

Stars

0 open issues

21 Apr 2026

Last commit

0 releases in 90 days

MIT

License

Python

Nothing serious here today

Today is the operative word: we check MCP LLM Gateway every 15 minutes and re-read its code on every release. Watch it and you find out the day that stops being true.

Connect this server

This server runs on your own machine — install it with the package manager and the client starts it for you. Package name taken from the official registry entry.

Claude Code Claude Desktop Codex Cursor VS Code

run in your terminal

claude mcp add mcp-llm-gateway -- uvx mcp-llm-gateway

~/Library/Application Support/Claude/claude_desktop_config.json

{
  "mcpServers": {
    "mcp-llm-gateway": {
      "args": [
        "mcp-llm-gateway"
      ],
      "command": "uvx"
    }
  }
}

~/.codex/config.toml

[mcp_servers.mcp-llm-gateway]
command = "uvx"
args = ["mcp-llm-gateway"]

.cursor/mcp.json

{
  "mcpServers": {
    "mcp-llm-gateway": {
      "args": [
        "mcp-llm-gateway"
      ],
      "command": "uvx"
    }
  }
}

.vscode/mcp.json

{
  "mcpServers": {
    "mcp-llm-gateway": {
      "args": [
        "mcp-llm-gateway"
      ],
      "command": "uvx"
    }
  }
}

Alternatives to MCP LLM Gateway

same job, measured the same way

Gate

by spideriq

SpiderIQ Gate: SpiderGate LLM gateway (completions, models, usage, traces)

53 installs/wk local only

Hubris

by hubris

OpenAI-compatible LLM gateway for Russia: 500+ models, ruble pricing, balance, chat.

47 installs/wk answering

freellmpool

by 0xzr

OpenAI-compatible MCP gateway cataloging 22 LLM providers, with routing, failover, and tools.

804 installs/wk local only

Correctover

by correctover

Compatibility MCP server package that forwards to the correctover-mcp-gateway runtime.

374 installs/wk local only

Authenticated Multi LLM Agent

by mikerawsonnz

Google-OAuth-gated LLM gateway: verify a Google ID token, then run a Gemini (Vertex AI) completion f

2 tools answering

Routara LLM Gateway

by 36412749-collab

OpenAI-compatible LLM, image and video APIs via Routara (api.routara.ai).

47 installs/wk local only

MCP Memory Gateway

by igorganapolsky

Pre-action gates that block AI agents from repeating known mistakes.

174 installs/wk local only

llmtrim

by fkiene

MCP server and proxy that compresses LLM prompts, tool output, and replies to cut token cost.

266 installs/wk local only

MCP LLM Gateway — questions

Answers built from our own checks of this server.

Why is there no uptime for MCP LLM Gateway?

MCP LLM Gateway runs on your own machine over stdio — there is no network address to reach, so uptime cannot be measured for it by anyone. What can be measured is adoption: the pypi package mcp-llm-gateway was installed 56 times last week.

How do I connect MCP LLM Gateway?

Copy the ready config from this page — we generate it for Claude Code, Claude Desktop, Codex, Cursor and VS Code, each with the file path that client actually reads. It runs locally, so the command pulls mcp-llm-gateway straight from pypi; nothing to host, nothing to sign up for.

How many people use MCP LLM Gateway?

The pypi package mcp-llm-gateway was installed 56 times in the last week. Week over week that is -14%. We show installs rather than GitHub stars on purpose: a star is a bookmark, an install is someone actually running it.

Is MCP LLM Gateway open source?

Yes — it is published under the MIT licence, written in Python and 0 stars on GitHub. The source link is on this page, so you can read exactly what it does with your data before you connect it.