# demesne

> demesne — jbeshir-demesne. Use this tool when you need to run and manage heterogeneous AI agents and shell commands in a secure and isolated environment. It solves problems related to agent deployment, dependency management, and resource isolation by utilizing local disposable OpenSandbox containers. The demesne tool accepts git repositories as input and provides a managed server interface for output, ideal for use cases requiring flexible and secure AI agent execution.

Canonical page: https://skillsregistry.net/skills/jbeshir-demesne  
JSON: https://api.skillsregistry.net/v1/skills/jbeshir-demesne

## Description

MCP server for running heterogeneous AI agents and shell commands in local disposable OpenSandbox containers

## Trust

- **Trust score (0–1):** 0.88
- **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/jbeshir/demesne)

## 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": "jbeshir-demesne"
    }
  }
}
```

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