# CodeBox-AI

> Use this tool when you need to securely execute Python code in a controlled environment, enabling large language models (LLMs) to run code, manage state, and access files. CodeBox-AI solves problems related to secure code execution, state management, and file access for LLM applications. It takes in Python code and file inputs, and outputs execution results, providing a secure interface for session-based code execution in Docker containers.

Canonical page: https://skillsregistry.net/skills/tomconte-codebox-ai  
JSON: https://api.skillsregistry.net/v1/skills/tomconte-codebox-ai

## Description

MCP server for secure, session-based Python code execution in Docker containers, enabling LLM applications to run code, manage state, and access files.

## Trust

- **Trust score (0–1):** 0.63
- **Verification tier:** scanned
- **Last scanned:** 2026-09-01

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-01

## Source

- **Source listing:** [Glama](https://glama.ai/mcp/servers/w8l1ekgw2i)
- **Repository:** <https://github.com/tomconte/codebox-ai>

## 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": "tomconte-codebox-ai"
    }
  }
}
```

REST: `GET https://api.skillsregistry.net/v1/skills/tomconte-codebox-ai` · pull for local use: `GET https://api.skillsregistry.net/v1/skills/tomconte-codebox-ai/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