# local-llm-mcp

> local-llm-mcp — naka-koma-local-llm-mcp. Use this tool when you need to offload tasks from MCP-compatible clients to local or cloud Large Language Models (LLMs) for efficient processing. It solves problems of scalability and accessibility by delegating lightweight tasks to suitable LLMs via LiteLLM, supporting models like Ollama and cloud APIs. The local-llm-mcp tool takes in tasks from clients like Claude Code and outputs processed results, ideal for use cases requiring flexible and distributed language model integration.

Canonical page: https://skillsregistry.net/skills/naka-koma-local-llm-mcp  
JSON: https://api.skillsregistry.net/v1/skills/naka-koma-local-llm-mcp

## Description

A thin MCP server that delegates lightweight tasks from Claude Code or any MCP-compatible client to local or cloud LLMs via LiteLLM, supporting models like Ollama and cloud APIs as subagents.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/i6ajbp1uq9)
- **Repository:** <https://github.com/naka-koma/local-llm-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": "naka-koma-local-llm-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/naka-koma-local-llm-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/naka-koma-local-llm-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