# dsh-mcp-control

> dsh-mcp-control — mochgolf-dsh-mcp-control. Use this tool when you need to control and monitor DeepSeek Harness sessions from Codex and other AI agents. It provides a local MCP server for managing sessions, allowing for seamless integration and interaction with AI agents. Ideal for use cases requiring centralized management of AI sessions, with inputs from AI agents and outputs to monitored sessions.

Canonical page: https://skillsregistry.net/skills/mochgolf-dsh-mcp-control  
JSON: https://api.skillsregistry.net/v1/skills/mochgolf-dsh-mcp-control

## Description

Local MCP server for controlling and monitoring DeepSeek Harness sessions from Codex and other AI agents

## Trust

- **Trust score (0–1):** 0.92
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

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

## Source

- **Source listing:** [GitHub](https://github.com/mochgolf/dsh-mcp-control)

## 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": "mochgolf-dsh-mcp-control"
    }
  }
}
```

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