Llm Router MCP Server

<picture> <source media="(prefers-color-scheme: dark)" srcset="assets/readme/hero-dark.svg"> <source media="(prefers-color-scheme: light)"

Remote serverstreamable-httpPython

What is the Llm Router MCP server?

. The llm router mcp server wraps that behind the Model Context Protocol, so an assistant can use it through 1 defined tool rather than through you.

What it actually does

  • You waste paid tokens on simple questions
  • You burn through Claude, Gemini, or OpenAI quota faster than necessary
  • You stop working when one provider is rate-limited or down

Its toolset

Everything the assistant can do here goes through one of these:

  • Category — Tools

Adding it to your client

Being a remote server, there is no local install. You register the endpoint with your client, authorise it once, and the tools appear.

Configuration

You will need 8 environment variables: OPENAI_API_KEY, GEMINI_API_KEY, OLLAMA_BASE_URL, OPENROUTER_API_KEY, LLM_ROUTER_POLICY, LLM_ROUTER_ENFORCE, LLM_ROUTER_PROFILE, LLM_ROUTER_BANDIT. The server will not start without them, which is usually why the tools fail to appear on a first run. Keep credentials in your client's env block or a secrets manager rather than in a file you might commit.

When to reach for it

Plenty of AI and media services servers cover similar ground. The differences that matter in practice are scope of access and how much setup stands between you and a working tool call. Llm Router's toolset — Category — is a fair guide to whether it matches your workflow. It is maintained by ypollak2; worth a glance at recent repository activity before you build anything load-bearing on it.

SyncDev reviews every entry in this directory against the project's own documentation before publishing, and revisits them as servers change.

Caveats

  • Your data travels to the provider's service, so the usual questions apply about what you send and what they retain.
  • Missing credentials fail quietly in some clients — if no tools show up, check the environment block first.
  • MCP clients confirm each tool call by default. Leave that on until you have watched what the llm router mcp server does with a few real requests.

Available tools

ToolWhat it does
CategoryTools

How to install the Llm Router MCP server

{
  "mcpServers": {
    "llm-router": {
      "command": "uvx",
      "args": ["llm-routing"],
      "env": {
        "OPENAI_API_KEY": "your-value",
        "GEMINI_API_KEY": "your-value",
        "OLLAMA_BASE_URL": "your-value",
        "OPENROUTER_API_KEY": "your-value",
        "LLM_ROUTER_POLICY": "your-value",
        "LLM_ROUTER_ENFORCE": "your-value",
        "LLM_ROUTER_PROFILE": "your-value",
        "LLM_ROUTER_BANDIT": "your-value"
      }
    }
  }
}

Add to claude_desktop_config.json, then restart Claude Desktop.

Configuration

VariableDescriptionRequired
OPENAI_API_KEYCredential the server authenticates with.Yes
GEMINI_API_KEYCredential the server authenticates with.Yes
OLLAMA_BASE_URLEndpoint or connection string the server talks to.Yes
OPENROUTER_API_KEYCredential the server authenticates with.Yes
LLM_ROUTER_POLICYConfiguration value read at startup.Optional
LLM_ROUTER_ENFORCEConfiguration value read at startup.Optional
LLM_ROUTER_PROFILEConfiguration value read at startup.Optional
LLM_ROUTER_BANDITConfiguration value read at startup.Optional

Example prompts to try

  • Use Llm Router to Category.

Frequently asked questions

It connects Llm Router to MCP-compatible AI assistants such as Claude and Cursor, exposing 1 tool (Category) that the assistant can call on your behalf. Instead of copying data back and forth by hand, the assistant works with Llm Router directly.