This MCP server enables AI agents to consult with multiple Ollama models for diverse perspectives, collaborative reasoning, and persistent memory management.
Core Capabilities:
Consult Individual Models - Send prompts to specific Ollama models with optional system prompts for guided reasoning
List Available Models - Discover all models available on your local or remote Ollama instance
Compare Multiple Models - Run identical prompts against multiple models simultaneously for side-by-side output comparisons
Sequential Reasoning Chains - Execute complex multi-step workflows where subsequent consultations build upon previous results
Persistent Memory Storage - Save consultation results (key, prompt, model, response) to configured memory services or local file storage for cross-session retrieval
Timeout Management - Configure specific time limits (60-600 seconds) for complex reasoning tasks without losing context
Flexible Integration - Works with any MCP-compatible client (like Claude Desktop) through the Model Context Protocol
Enables consulting with Ollama models for alternative reasoning viewpoints, with tools for sending prompts to models and listing available models on the Ollama instance.
MCP Ollama Consult Server
An MCP (Model Context Protocol) server that allows consulting with Ollama models for reasoning from alternative viewpoints.
Features
consult_ollama: Send prompts to Ollama models and get responses
list_ollama_models: List available models on the local Ollama instance
Installation
Ensure you have Node.js installed
Install dependencies:
npm installBuild the project:
npm run build
Usage
Make sure Ollama is running locally (default: (http://localhost:11434).
Start the MCP server:
Or for development:
Configuration
Set the OLLAMA_BASE_URL environment variable to change the Ollama endpoint:
Docker
To run with Docker, build the image:
Requirements
Node.js 18+
Ollama running locally or accessible via HTTP