Model Context Protocol moderate risk

Multi AI Advisor

Queries multiple Ollama models to provide diverse AI perspectives, synthesizing responses for comprehensive answers, enhancing Claude's advisory capabilities.

Connections & Capabilities

Connects To

GitHub

Capabilities

read

Quickstart

Install

npx -y @smithery/cli install @YuChenSSR/multi-ai-advisor-mcp --client claude

Config

{
  "mcpServers": {
    "multi-model-advisor": {
      "command": "node",
      "args": ["/absolute/path/to/multi-ai-advisor-mcp/build/index.js"]
    }
  }
}

Exposed MCP Tools (2)

safe

list-available-models

Lists all available Ollama models on the system.

Read-only operation, no side effects.

moderate

query-models

Queries multiple specified Ollama models with a given question.

Queries models, potentially leading to resource exhaustion or unexpected outputs if prompts are malicious.

Safety Assessment

This MCP server is relatively safe for querying local models. However, the lack of authentication and potential for prompt injection require careful configuration and monitoring. It's safest when used with trusted models and well-defined system prompts.

Read-only access to Ollama models
No direct internet access
Configuration through environment variables
Limited write operations (model querying)
Requires local Ollama instance

Potential for prompt injection if system prompts are not carefully managed
Ollama API URL needs to be secured
Reliance on local Ollama instance introduces a single point of failure
No built-in authentication mechanism
Exposure of local models to queries