ollama-cli

Manage local LLM lifecycle by listing, pulling, and running models via the ollama CLI.

3|1|Updated Apr 12, 2026

Search Tags:#troubleshooting #model management #ollama #mcp configuration #local llm #agent launch #shell usage

Ready to run

npx skills add https://github.com/Cogni-AI-OU/cogni-ai-agent-skills --skill ollama-cli

💬 Prompt for ChatGPT / Claude Chat▼

Please help me install this Agent Skill.
Skill: ollama-cli
Source: https://github.com/Cogni-AI-OU/cogni-ai-agent-skills/tree/main/ollama-cli
Command: npx skills add https://github.com/Cogni-AI-OU/cogni-ai-agent-skills --skill ollama-cli

SYSTEM DOCUMENTATION & REQUIREMENTS

What problem does it solve?

Ollama CLI procedures reduce the friction of getting local LLMs running reliably, including pulling missing models and starting agent workflows with MCP-ready configurations.

Core Features & Use Cases

Local model verification and caching: list installed models and pull a specific model before use to avoid initialization failures.
Interactive and agent-oriented execution: run models for quick tests and launch model-backed tools/agents that integrate with Model Context Protocol (MCP).
Safer configuration injection for agents: pass inline MCP configuration to wrapper launch commands in a shell-compatible way, avoiding common syntax issues.

Quick Start

Use the ollama-cli skill to pull the model gemma4:e2b and verify it is available with the command ollama list.

Frequently Asked Questions about ollama-cli

High-intent search queries and answers about installing and using this skill.

FAQPage Schema

How do I list installed local LLMs and pull missing models using Ollama?▼

To manage local LLMs with Ollama, you can list installed models and pull missing ones via the ollama CLI. This verifies cached models before use to prevent initialization failures during agent setup.

How do I pass MCP configuration to Ollama agents without shell syntax errors?▼

You can pass inline MCP configuration to Ollama wrapper launch commands using shell-compatible dynamic JSON injection. This avoids common syntax issues when starting model-backed agents that require MCP integration.

Why does my local LLM agent launch fail when using Ollama?▼

Local LLM agent launches fail when models are unpulled, shell syntax is incorrect, or system resources are exhausted. The Ollama CLI mitigates these issues by verifying models and applying safer configuration injection.

Do I need the Ollama daemon running to launch local inference sessions?▼

Yes, the Ollama daemon must be reachable to launch local inference sessions and manage the local LLM lifecycle. This ensures the backend can verify cached models and execute interactive runs successfully.

Can I use Ollama to run quick tests and launch model-backed tools?▼

Yes, Ollama supports interactive execution for quick tests and launching model-backed tools or agents. It manages the local LLM lifecycle to ensure the required models are cached and available for operations.