# ToolSmith

> ToolSmith — rockyrocks-toolsmith. Use this tool when you need to integrate large language models (LLMs) with custom tools and remote servers, bridging disparate systems through a unified protocol layer. It solves problems of compatibility and scalability, enabling seamless interaction between LLMs like Claude, GPT, and Gemini with custom skills and networks. It accepts LLM inputs and outputs unified protocol data, ideal for use cases requiring flexible and standardized model integration.

Canonical page: https://skillsregistry.net/skills/rockyrocks-toolsmith  
JSON: https://api.skillsregistry.net/v1/skills/rockyrocks-toolsmith

## Description

This project is a production-ready MCP server that bridges any LLM — Claude, GPT, Gemini, or open-source models with custom tools, prompt-driven skills, and remote server networks through a single, unified protocol layer.

## Trust

- **Trust score (0–1):** 0.98
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Updated:** 2026-09-28

## Source

- **Source listing:** [GitHub](https://github.com/RockyRocks/ToolSmith)

## 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": "rockyrocks-toolsmith"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/rockyrocks-toolsmith` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/rockyrocks-toolsmith/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