# mainframe-mcp

> mainframe-mcp — sushihex-mainframe-mcp. Use this tool when you need to leverage local knowledge and persistent memory for coding tasks, or require GPU-accelerated hybrid search with source citations. It solves problems related to efficient code retrieval and search, providing a low VRAM footprint. Ideal for use cases involving git, where a shared MCP daemon powers the search functionality.

Canonical page: https://skillsregistry.net/skills/sushihex-mainframe-mcp  
JSON: https://api.skillsregistry.net/v1/skills/sushihex-mainframe-mcp

## Description

100% local knowledge and persistent memory for coding agents. GPU-accelerated hybrid search with source citations and a low VRAM footprint, powered by one shared MCP daemon.

## Trust

- **Trust score (0–1):** 0.30
- **Verification tier:** scanned
- **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/sushiHex/mainframe-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": "sushihex-mainframe-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/sushihex-mainframe-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/sushihex-mainframe-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