# local-executor-mcp

> Use this tool when you need to optimize mechanical code generation tasks and reduce token usage for frontier models. The local-executor-mcp server delegates subtasks to a local Large Language Model (LLM) served by llama-swap, providing an efficient interface for inputting code generation requests and outputting generated code. It solves problems related to token conservation and streamlined code generation for frontier planners like Claude Code.

Canonical page: https://skillsregistry.net/skills/rasvan-ghiliciu-test-mcp  
JSON: https://api.skillsregistry.net/v1/skills/rasvan-ghiliciu-test-mcp

## Description

An MCP server that lets a frontier planner (Claude Code) delegate mechanical code-generation subtasks to a local LLM served by llama-swap, to save frontier-model tokens.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-31

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** ai-ml
- **Updated:** 2026-08-31

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/xtfw7yb0if)
- **Repository:** <https://github.com/rasvan-ghiliciu/test_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": "rasvan-ghiliciu-test-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rasvan-ghiliciu-test-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rasvan-ghiliciu-test-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