# Ollama MCP Server

> Use this tool when you need to offload computationally intensive tasks like code generation, text drafting, and embedding to local GPUs, or require multi-turn conversation support and model management. It exposes local Ollama instances as tools for Claude Code, enabling efficient task processing and management. Ideal for use cases involving resource-intensive language model tasks, model context management, and optimized GPU utilization.

Canonical page: https://skillsregistry.net/skills/jmrussas-ollama-mcp  
JSON: https://api.skillsregistry.net/v1/skills/jmrussas-ollama-mcp

## Description

Exposes local Ollama instances as tools for Claude Code, allowing users to offload code generation, text drafting, and embedding tasks to local GPUs. It supports multi-turn conversations and model management through the Model Context Protocol.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-19

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/nxgzn52ohj)
- **Repository:** <https://github.com/JMRussas/ollama-mcp>

## Use it

Resolve this record through the SkillsRegistry MCP server (no auth, read-only):

```
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp
```

```json
{
  "jsonrpc": "2.0",
  "id": 1,
  "method": "tools/call",
  "params": {
    "name": "get_skill",
    "arguments": {
      "slug": "jmrussas-ollama-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/jmrussas-ollama-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/jmrussas-ollama-mcp/pull`

---
SkillsRegistry indexes agent skills from public registries and GitHub. Skills we have analysed are scanned with Circle-IR and scored on six dimensions; each listing states its scan coverage. More: https://skillsregistry.net/llms.txt