# dsh-mcp

> dsh-mcp — mr-potato-123-dsh-mcp. Use this tool when you need to optimize MCP agent performance by reducing cost and latency. It delegates file operations and command runs to a local DeepSeek Harness, allowing the parent agent to focus on planning and reasoning. Ideal for applications requiring fast execution and minimal overhead, dsh-mcp provides a efficient execution layer for MCP agents.

Canonical page: https://skillsregistry.net/skills/mr-potato-123-dsh-mcp  
JSON: https://api.skillsregistry.net/v1/skills/mr-potato-123-dsh-mcp

## Description

A cheap, fast execution layer for MCP agents that delegates file reads, edits, and command runs to a local DeepSeek Harness, reducing cost and latency while keeping the parent agent in control of planning and reasoning.

## Trust

- **Trust score (0–1):** 0.66
- **Verification tier:** scanned
- **Last scanned:** 2026-08-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** file-system
- **Updated:** 2026-08-28

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/x8gr96q5w3)
- **Repository:** <https://github.com/Mr-potato-123/dsh-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": "mr-potato-123-dsh-mcp"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/mr-potato-123-dsh-mcp` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/mr-potato-123-dsh-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