# LocalLLM-MCP

> LocalLLM-MCP — amit11-ibm-localllm-mcp-github. Use this tool when you need to interact with local LLM models like Granite, Nemotron, and Llama through natural language in VS Code. It solves the problem of integrating these models with IBM Bob by exposing them via STDIO, allowing for easy configuration and management through a single models.json file. This enables seamless interaction with various LLM models without requiring code changes.

Canonical page: https://skillsregistry.net/skills/amit11-ibm-localllm-mcp-github  
JSON: https://api.skillsregistry.net/v1/skills/amit11-ibm-localllm-mcp-github

## Description

MCP server that exposes local llama.cpp LLM models to IBM Bob in VS Code via STDIO, enabling natural language interaction with models like Granite, Nemotron, Gemma, Qwen, and Llama. Configuration is managed through a single models.json file, making it easy to add or disable models without code changes.

## Trust

- **Trust score (0–1):** 0.68
- **Verification tier:** scanned
- **Last scanned:** 2026-09-03

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-09-03

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/wyt6q1zhc2)
- **Repository:** <https://github.com/amit11-ibm/LocalLLM-MCP-GITHUB>

## 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": "amit11-ibm-localllm-mcp-github"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/amit11-ibm-localllm-mcp-github` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/amit11-ibm-localllm-mcp-github/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