How do I get an API key for return0?
Visit the [return0 documentation](https://getreturn0.com/docs) to obtain your API key. You can also use `"demo"` for testing purposes.

@getreturn0
Basic information
Debug your remote Node.js and Next.js applications directly from your AI IDE like Cursor.
Add this server to your MCP-compatible client using the configuration below.
{
"mcpServers": {
"return0": {
"command": "npx",
"args": [
"-y",
"@return-0/mcp-server"
],
"env": {
"RETURN0_API_KEY": "YOUR-API-KEY"
}
}
}
}Tool list not available yet
This listing does not currently have a tool list to display. This does not mean the server has no tools; check its documentation for supported capabilities.
Fetch the live tool list by running this server in a temporary sandbox using the button above.
return0 is an MCP server for debugging production Node.js applications in real-time. It integrates with Cursor IDE to monitor variables, observe execution flow, and understand runtime behavior in live environments, especially for Next.js apps deployed on platforms like Vercel.
Install by configuring the MCP server in Cursor IDE. Use the one‑click install button or manual setup by adding a server named return0 with command npx, args -y @return-0/mcp-server, and environment variable RETURN0_API_KEY set to your API key. Provide an API key (or "demo" for testing) to authenticate.
variable_extractor tool for extracting runtime variable values.Visit the [return0 documentation](https://getreturn0.com/docs) to obtain your API key. You can also use `"demo"` for testing purposes.
It provides a `variable_extractor` tool that extracts the runtime value, type, and timestamp of variables from production code based on file paths and variable names with line numbers.
You can either use the one‑click installation button or manually add a server with name `return0`, command `npx`, args `-y @return-0/mcp-server`, and the environment variable `RETURN0_API_KEY`. See the manual configuration steps in the README.
Node.js and npm are required because the server runs via `npx` and is installed automatically when Cursor starts.
The MCP server reads source files from your local filesystem and connects to your running production application to retrieve live variable values. Data is not stored persistently by the server.


Verified distributed compute for humans, applications, and agents. Submit Blender, Octane, and video workloads, route them across qualified GPUs, track asynchronous execution, download finished artifacts, and verify FARP

Verified cyber-physical AI tools. 25 MCP tools, x402-payable on Base.

SSH MCP server for AI agents: remote commands, file transfer, log search and server audits through OpenSSH.

Know when your AI agents, cron jobs and CI pipelines fail, stall or go quiet. Your agent sets up monitors from a plain description, tells you what is broken and why, reads run history and traces, and writes notes on inci
Comments