# Local Model Workers MCP

> Local Model Workers MCP — gaabrielrd-local-model-workers-mcp. Use this tool when you need to securely delegate repository exploration and test proposals to a remote model while maintaining read-only access and enforcing security boundaries. It solves problems related to secure collaboration and testing, allowing models like Claude Code and Codex to work with repositories without compromising security. The tool takes in repository data and test proposals as inputs and outputs secure, read-only exploration results.

Canonical page: https://skillsregistry.net/skills/gaabrielrd-local-model-workers-mcp  
JSON: https://api.skillsregistry.net/v1/skills/gaabrielrd-local-model-workers-mcp

## Description

A local MCP server that lets Claude Code and Codex delegate repository exploration and test proposals to a remote LM Studio model, while enforcing security boundaries by keeping all repository access read-only and never applying patches or running commands remotely.

## Trust

- **Trust score (0–1):** 0.69
- **Verification tier:** scanned
- **Last scanned:** 2026-08-29

## Facts

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

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/o7tzqmgsls)
- **Repository:** <https://github.com/gaabrielrd/local-model-workers-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": "gaabrielrd-local-model-workers-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/gaabrielrd-local-model-workers-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/gaabrielrd-local-model-workers-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