# mcp-exec

> mcp-exec — inhuman-mcp-exec. Use this tool when you need to execute custom Python code in a secure, isolated environment, solving problems such as remote code execution and sandboxing. It takes in Python code and optional authentication as input, and outputs stdout, stderr, and exit code through stdio, HTTP, or SSE transports. Ideal for use cases requiring network-isolated code execution with flexible transport options.

Canonical page: https://skillsregistry.net/skills/inhuman-mcp-exec  
JSON: https://api.skillsregistry.net/v1/skills/inhuman-mcp-exec

## Description

MCP server that executes caller-supplied Python code in a network-isolated, locked-down sandbox and returns stdout/stderr/exit code. Supports stdio, HTTP, and SSE transports with optional auth.

## Trust

- **Trust score (0–1):** 0.70
- **Verification tier:** verified
- **Last scanned:** 2026-08-29

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** other
- **Updated:** 2026-08-29

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/ogt1lx5bov)
- **Repository:** <https://github.com/inhuman/mcp-exec>

## 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": "inhuman-mcp-exec"
    }
  }
}
```

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