# mcp-ollama

> Use this tool when you need to offload computationally expensive tasks from API-priced orchestrators to a local environment, leveraging Ollama models for tasks such as text generation, summarization, and code analysis. It provides a range of stdio tools for tasks like drafting, code review, and mechanical transforms, with inputs and outputs via standard input/output streams. Ideal for use cases where cost savings and local control are essential, such as large-scale development projects or high-volume API workloads.

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

## Description

MCP server wrapping local Ollama models for offload from API-priced orchestrators.

Nine stdio tools -  generation, summarisation, analysis, drafting, code tasks (docstring/test/explain/review/types/refactor-suggest), diff-driven tasks (commit-message/pr-description/changelog/summary/impact), mechanical transforms, and model management (list/pull).

Apache-2.0.

## Trust

- **Trust score (0–1):** 0.96
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/g3kcg3omnn)
- **Repository:** <https://github.com/true-alter/mcp-ollama>

## 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": "true-alter-mcp-ollama"
    }
  }
}
```

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