tool-sandbox-mcp

domdomegg/tool-sandbox-mcp
★ 1 stars TypeScript 🤖 AI/LLM Updated today
📦 MCP server that runs agent code in a sandbox with access to upstream MCP tools
View on GitHub →

Quick Install

Copy the config for your editor. Some servers may need additional setup — check the README.

Add to claude_desktop_config.json:

{
  "mcpServers": {
    "tool-sandbox-mcp": {
      "command": "npx",
      "args": [
        "-y",
        "domdomegg/tool-sandbox-mcp"
      ]
    }
  }
}

README Excerpt

> Give your AI agent a single `execute_code` tool that can call any of your upstream MCP tools — more efficiently. When agents call tools directly, every tool definition and intermediate result flows through the context window. As I wrote about in [code execution with MCP](https://www.anthropic.com/engineering/code-execution-with-mcp), this gets expensive fast: hundreds of tool definitions consume tokens upfront, and intermediate results (like full documents being copied between tools) bloat the

Tools (6)

hostissuerUrlportselfPrefixstoreupstream