Multi-LLM MCP server for Claude Code & Codex — route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware
Connect External to Claude, Cursor or any other MCP client and it stops being a tab you switch to. Multi-LLM MCP server for Claude Code & Codex — route AI agent work across 20+ low-cost provider buckets with round-robin dispatch and quota-aware fallback. The external mcp server is what makes that connection.
Your Google + Groq + OpenRouter + Ollama Cloud free tiers, plus cheap direct APIs like DeepSeek, all have separate provider buckets. external-agents treats them as one pool: round-robin dispatch, cooldown-aware, auto-fallback on 429. Same agentic workload that used to cost $10-100/day on one premium model can often run at effectively $0-very-low-cost. Also the perfect substrate for LLM-Council-style multi-model panels — pick_agents gives you N distinct-provider picks in one call.
external-agents is one piece of Mrrlin — an AI orchestration platform for solo developers and small teams. If you like this package, you'll probably like the rest of Mrrlin.
@mrrlin-dev/external-agents on npm is all you need. Most clients run it directly, so configuration is a few lines and a restart.
The toolset is worth reading before you wire it up, because it tells you what the integration is really for:
Multi — step debugging with unclear root causeCodex — cursor-agentkiro-cli — The kiro-cli tool exposed by this serverConfiguration is passed through the environment: GROQ_API_KEY. Treat anything key-shaped as a real credential — scope it to the minimum the server needs, and rotate it if it ever lands in a shared config.
Among the AI and media services options, the useful question is rarely "what can it do" but "what does it cost you to run" — permissions, credentials, and how much of your context its toolset consumes. External's toolset — Multi, Codex, kiro-cli — is a fair guide to whether it matches your workflow. It is maintained by aiuxsolutions; 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.
| Tool | What it does |
|---|---|
| Multi | step debugging with unclear root cause |
| Codex | **cursor-agent** |
| kiro-cli | The kiro-cli tool exposed by this server. |
{
"mcpServers": {
"external-agents": {
"command": "npx",
"args": ["-y", "@mrrlin-dev/external-agents"],
"env": {
"GROQ_API_KEY": "your-value"
}
}
}
}Add to claude_desktop_config.json, then restart Claude Desktop.
| Variable | Description | Required |
|---|---|---|
| GROQ_API_KEY | Credential the server authenticates with. | Yes |
Build a programmable telecommunications stack for connecting telephony services with the Internet via a cloud-based utility.
Search built for AI, not humans — semantic web search that returns model-ready content, plus code context.
Answers, not links — delegate questions to Perplexity's search-grounded models and get cited responses back.
Give your assistant a voice — text-to-speech, voice cloning and audio tools from the ElevenLabs API.
Give your assistant a real code sandbox — isolated cloud VMs for actually running the code it writes.
The ML hub in your context window — search models, datasets, papers and run Spaces from the official server.