Ollama Mcp Server

AI LLM actor for text generation using Llama 3.x models.

What does Ollama MCP Server do?

Ollama MCP Server is an AI-powered actor that provides powerful language model capabilities through a simple API. It enables users to generate text using state-of-the-art models like Llama 3.3 70B.

Simply enter your prompts, choose a model, and get AI-generated results in seconds.

Why use Ollama MCP Server?

🚀 Powerful AI Models

• 6 state-of-the-art models including Llama 3.3 70B and Llama 3.1
• Optimized for various use cases

💰 Pay-Per-Event Pricing

• Only pay for successful chat completions
• $0.0075 per request
• No subscription required

🔧 Flexible Configuration

• Customizable system prompts
• Adjustable temperature and token limits
• Multiple model options

🤖 MCP Integration

• Works as a tool for AI agents via Model Context Protocol
• Enhanced discoverability on Apify Store

How much does it cost to use Ollama MCP Server?

The actor uses pay-per-event pricing. You are charged only when a chat completion is successfully generated.

Event	Price	Description
chat_completion	$0.0075	Per successful AI response

That's only $7.50 per 1,000 requests!

Cost Examples

Requests	Cost
100	$0.75
1,000	$7.50
10,000	$75.00

Note: Platform usage costs (compute, memory) are included in the event price. You only pay for successful completions.

How to use Ollama MCP Server

Quick Start

1. Enter system prompt to define AI behavior (optional)
2. Enter user prompt with your question or request
3. Choose a model (default: Llama 3.3 70B)
4. Run and get results

Example

System Prompt: You are a helpful AI assistant.
User Prompt: Explain quantum computing in simple terms.
Model: meta/llama-3.3-70b-instruct

Input

Parameter	Type	Default	Description
systemPrompt	textarea	"You are a helpful AI assistant."	Define AI behavior and context
userPrompt	textarea	-	Your question or request
model	select	meta/llama-3.3-70b-instruct	AI model to use
maxTokens	integer	2048	Maximum tokens to generate
temperature	number	0.7	Sampling temperature (0-2)

Available Models

Model	Best For
meta/llama-3.3-70b-instruct	High-quality text generation
meta/llama-3.1-8b-instruct	Fast, efficient completions
meta/llama-3.1-70b-instruct	Complex reasoning tasks
meta/llama-3.2-3b-instruct	Lightweight applications
meta/llama3-8b-instruct	General purpose
meta/llama3-70b-instruct	Complex tasks

Output

Results are saved to the dataset. You can download in JSON, CSV, or Excel format.

Example Output

{
  "model": "meta/llama-3.3-70b-instruct",
  "systemPrompt": "You are a helpful AI assistant.",
  "userPrompt": "Explain quantum computing in simple terms.",
  "response": "Quantum computing is a type of computing that uses quantum mechanics...",
  "usage": {
    "prompt_tokens": 25,
    "completion_tokens": 150,
    "total_tokens": 175
  }
}

Tips for Best Results

🎯 Model Selection

• Fast & simple: llama-3.1-8b-instruct
• Best quality: llama-3.3-70b-instruct

🌡️ Temperature Settings

• 0.1-0.3 for factual, focused responses
• 0.5-0.7 for balanced creativity
• 0.8-1.0 for creative writing

📝 System Prompts

• Be specific about the AI's role
• Include relevant context
• Set the desired output format

FAQ

Is Ollama MCP Server free to try?

Yes! You can try the actor on the Apify free plan. Check Apify pricing for free plan limits.

Which model should I use?

• Fast tasks: llama-3.1-8b-instruct
• Best quality: llama-3.3-70b-instruct

What is the system prompt for?

The system prompt defines how the AI should behave. Use it to set the AI's role, personality, or output format.

Is there a spending limit?

Yes! You can set a maximum cost per run in Apify Console. The actor will stop when the limit is reached.

What happens if a request fails?

You are only charged for successful chat completions. Failed requests do not incur charges.

Can I use this with AI agents?

Yes! This actor supports MCP (Model Context Protocol) integration, making it available as a tool for AI agents.

Support

• Apify Documentation
• Report Issues via Issues tab

---

Ollama MCP Server - Power your applications with state-of-the-art AI models.