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.
Install
npx -y fetchsandbox-mcp
Paste the configuration above into your MCP client config (claude_desktop_config.json for Claude Desktop) and restart the client.
{
"mcpServers": {
"mcp": {
"command": "npx",
"args": [
"-y",
"fetchsandbox-mcp"
],
"env": {
"FETCHSANDBOX_BASE_URL": "<FETCHSANDBOX_BASE_URL>",
"FETCHSANDBOX_TELEMETRY": "<FETCHSANDBOX_TELEMETRY>"
}
}
}
}Paste the configuration above into your MCP client config (claude_desktop_config.json for Claude Desktop) and restart the client.
Sources: public MCP Server directories. This is an independent third-party directory with no affiliation to or endorsement from the maintainers of the listed servers.
