@mrrlin-dev/external-agents

MCP server routing workloads across 20+ LLM providers with round-robin dispatch, cooldown-aware fallback, and quota-aware cost control.

AI & ML

Install Command

npx -y @mrrlin-dev/external-agents

Claude Desktop Config

{
  "mcpServers": {
    "mrrlin-dev-external-agents": {
      "command": "npx",
      "args": [
        "-y",
        "@mrrlin-dev/external-agents"
      ]
    }
  }
}

@mrrlin-dev/external-agents is a community MCP server that connects AI assistants like Claude to mcp server routing workloads across 20+ llm providers with round-robin dispatch, cooldown-aware fallback, and quota-aware cost control. It runs locally on your machine, keeping your data private and giving you full control over the connection. AI engineers can use it to chain models and pipelines into more powerful workflows.

About @mrrlin-dev/external-agents

Overview

MCP server routing workloads across 20+ LLM providers with round-robin dispatch, cooldown-aware fallback, and quota-aware cost control.

Topics

mcp, mcp-server, model-context-protocol, llm-router, multi-provider, free-tier, cost-optimization, rate-limit, claude, codex, gemini, groq, openrouter, deepseek, ollama

Who Should Use @mrrlin-dev/external-agents?

1Chain AI models and pipelines through a unified MCP interface
2Let Claude orchestrate other AI tools and models
3Integrate embeddings, image generation, or speech APIs into your workflow
4Build multi-model workflows without writing custom integration code

How to Install @mrrlin-dev/external-agents

Before you start

You will need Node.js (v18 or later) installed on your machine — download it from nodejs.org if you haven't already.

1Open a terminal (Terminal on Mac, Command Prompt or PowerShell on Windows).
2Paste the install command above and press Enter — Node.js will download and run the server automatically.
3Add the server to your Claude Desktop config file (see the JSON snippet above) and restart Claude.

The Claude Desktop config snippet above can be copied and pasted directly into your claude_desktop_config.json file — no editing required.