list-available-modelsLABSCO SUMMARY
A council of local models, not a router.
This is not load balancing — the point is disagreement. Three small models with three different system prompts produce three framings of the same question, and the assistant that called them does the synthesis. Everything runs against your own Ollama instance, so the cost is RAM rather than tokens.
What it is
An MCP server that fans one question out to multiple Ollama models running on your machine and returns all of their responses together. Each model can carry a different system prompt, so the answers come back from deliberately different angles rather than as three paraphrases.
What you get
- Every Ollama model installed on the system listed, with the configured defaults marked —
list-available-models - One question sent to several models at once, their responses returned side by side —
query-models - A persona per model, set through per-model system prompts in
.env— the shipped example gives one creative, one supportive and one analytical framing - The default roster set once in
DEFAULT_MODELS, or chosen per question in the request
Requirements
Ollama installed and running, with the models pulled beforehand — the README's example roster is gemma3:1b, llama3.2:1b and deepseek-r1:1.5b. Node.js 16.x or higher. OLLAMA_API_URL points at the Ollama endpoint (http://localhost:11434 in the example), DEFAULT_MODELS lists the roster, and GEMMA_SYSTEM_PROMPT, LLAMA_SYSTEM_PROMPT and DEEPSEEK_SYSTEM_PROMPT set the personas. Install is a clone plus npm install and npm run build, then launching build/index.js with node; the package.json names it multi-model-advisor at 1.0.0. Running several models at once takes memory — pick smaller models if a manager model has already claimed most of it.
Setup effort
Build from source — git clone https://github.com/YuChenSSR/multi-ai-advisor-mcp.git
USE CASES
01
Pressure-testing a decision
Put the question to models primed to be creative, supportive and analytical, and read where they disagree.
02
Seeing what your machine can actually run
List the installed Ollama models and check which ones are wired in as defaults before composing a roster.
03
Getting a second view without a second bill
Route the extra opinions to local models so the comparison costs nothing beyond the hardware.
04
Choosing the panel per question
Name the models you want in the request instead of always using the configured default roster.
2 tools
Listed in project docs. Your client may show a different list.
query-modelsBEFORE YOU INSTALL
What to know first
Tools you get
2 tools named in the project's documentation.
Requires
- Node.js 16.x or higher
- Ollama installed and running, with the models pulled
Where it runs
The documented client runs the server on your machine.
INSTALLATION
Connect your client
You clone and build this one yourself.
Server setup
TERMINAL
git clone https://github.com/YuChenSSR/multi-ai-advisor-mcp.git
cd multi-ai-advisor-mcp
npm install
npm run build
ollama pull gemma3:1b
ollama pull llama3.2:1b
ollama pull deepseek-r1:1.5bOptional: the README's .env settings (OLLAMA_API_URL, DEFAULT_MODELS, one system prompt per model) all have built-in defaults — http://localhost:11434 and the three models above
Alternatively, skip the build and let Smithery install it into Claude Desktop:
TERMINAL
npx -y @smithery/cli install @YuChenSSR/multi-ai-advisor-mcp --client claudeMCP Clients
Claude Desktop
CLAUDE DESKTOP · JSON
{
"mcpServers": {
"multi-model-advisor": {
"command": "node",
"args": [
"<YOUR_PATH_TO_MULTI_AI_ADVISOR_MCP>/build/index.js"
]
}
}
}
