# AgentExec

> Use this tool when you need to securely execute user code in sandboxed environments, supporting multiple programming languages and package managers. AgentExec solves problems of code execution safety and isolation, making it ideal for AI coding assistants, educational platforms, and development workflows. It accepts code inputs and returns execution outputs, with configurable controls and transport methods, allowing for seamless integration into various applications and use cases.

Canonical page: https://skillsregistry.net/skills/realugbun-agentexec  
JSON: https://api.skillsregistry.net/v1/skills/realugbun-agentexec

## Description

AgentExecMCP is a FastMCP-based execution server that provides AI assistants with secure sandboxed code execution capabilities across Python, Node.js, and Go environments, along with shell command execution and package management through pip, npm, and Go modules. Built by realugbun using Python with comprehensive safety controls including configurable timeouts (1-300 seconds), process cleanup, input size validation, and workspace isolation, the implementation features automatic temporary file management for code execution, special Go compilation handling with CGO_ENABLED=0, and concurrency controls with semaphore-based resource management. The server supports multiple transport methods (stdio, SSE, streamable HTTP) and runs in a Docker container with pre-installed development environments, making it valuable for AI coding assistants that need to execute user code safely, educational platforms requiring isolated code execution, and development workflows where AI agents need to run scripts, install dependencies, and perform system operations within controlled sandbox environments.

## Trust

- **Trust score (0–1):** 0.97
- **Verification tier:** verified
- **Last scanned:** 2026-09-28

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** mcp-remote
- **Runtime environment:** api
- **Category:** cloud-infra
- **Updated:** 2026-09-28

## Source

- **Source listing:** [PulseMCP](https://www.pulsemcp.com/servers/realugbun-agentexec)
- **Repository:** <https://github.com/realugbun/agentexecmcp>

## 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": "realugbun-agentexec"
    }
  }
}
```

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