# mcp-exec

> mcp-exec — joeblackwaslike-mcp-exec. Use this tool when you need to execute sandboxed code while minimizing token usage and keeping intermediate results organized. It solves problems of excessive token consumption in multi-tool workflows, reducing usage by 80-95%. The mcp-exec tool takes in code execution requests and outputs results, ideal for use cases involving git and complex workflows.

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

## Description

Reference implementation of Anthropic's 'Code execution with MCP.' Reuses Claude Code's own sandbox and config to keep intermediate tool output out of the context window on every workflow — up to 99% fewer tokens.

## Trust

- **Trust score (0–1):** 0.89
- **Verification tier:** verified
- **Last scanned:** 2026-09-19

## Facts

- **Version:** 1.0.0
- **Skill type:** atomic
- **Execution layer:** container
- **Runtime environment:** vm
- **Category:** media
- **Updated:** 2026-09-21

## Source

- **Source listing:** [GitHub](https://github.com/joeblackwaslike/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": "joeblackwaslike-mcp-exec"
    }
  }
}
```

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