fetchsandbox-mcp
A deterministic eval engine for coding agents. Your agent claims it fixed the bug—this checks it. The same scenario runs twice against a sandbox of the services your code calls, with failures injected on purpose. It must fail on the old code and pass on the new. The verdict is an exit code, not a model's opinion. Every run leaves a receipt.
AI 智能体
npm 0 个平台
0 项功能
安装
npx -y fetchsandbox-mcp
把上面的配置写入 MCP 客户端的配置文件（Claude Desktop 为 claude_desktop_config.json），重启客户端后生效。
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"fetchsandbox-mcp"
],
"env": {
"FETCHSANDBOX_BASE_URL": "<FETCHSANDBOX_BASE_URL>",
"FETCHSANDBOX_TELEMETRY": "<FETCHSANDBOX_TELEMETRY>"
}
}
}
}把上面的配置写入 MCP 客户端的配置文件（Claude Desktop 为 claude_desktop_config.json），重启客户端后生效。
数据来源：公开的 MCP Server 目录。本站为独立第三方目录，与各 MCP Server 维护方均无隶属或背书关系；名称与简介如实标注，介绍文案由本站再加工。
