Deploy from Cursor to a live URL with MCP

Yes, once it has a tool that does the deploying. Cursor writes and runs code but does not host the result. Add ProductEcho to Cursor as an MCP server and one prompt is enough: the agent reads your project, creates a PostgreSQL database if the app needs one, uploads the code, deploys it, and gives you a public HTTPS URL.

This page is about deploying apps and websites you built in Cursor, not about installing Cursor itself.

The quickest way is one click. On a computer with Cursor installed, select Add ProductEcho to Cursor. Cursor opens and asks you to confirm adding the MCP server.

To add it by hand instead, put the server in Cursor's MCP config. Use ~/.cursor/mcp.json to have it in every project, or .cursor/mcp.json inside one project.

{
  "mcpServers": {
    "productecho": {
      "url": "https://api.productecho.com/mcp"
    }
  }
}

Whichever way you add it, if ProductEcho does not appear in Cursor's MCP settings, restart Cursor. Cursor then opens a browser window where you sign in and approve access to your ProductEcho workspace. The consent covers workspace discovery, deployments and database management, and no API key is involved.

The MCP server gives Cursor the tools. The skills give the agent ProductEcho's instructions for using them: how to inspect a project, what each runtime needs, and how to create and wire a database. Install them once:

npx -y skills add productecho/skills --skill '*' --yes --global --agent cursor

This copies four skills into ~/.agents/skills, a folder Cursor loads. In Agent chat, type / and search for productecho-deploy to run one by name. You can also just ask in plain language, and the agent picks the skill when it fits.

Open your project in Cursor, open Agent chat and run:

Deploy this app to ProductEcho with PostgreSQL and give me the live HTTPS URL.

Drop "with PostgreSQL" if the app has no database. To call the skill by name, start the message with /productecho-deploy. Cursor asks for approval before it runs an MCP tool by default, and you can click the arrow next to the tool name to see what it is about to send. When the deploy finishes, the agent prints the URL.

app.productecho.com/dashboard/deploymentsFull size

Each step and status, from upload to live URL, is explained in How a deploy works.

Server apps run as containers and single-page apps that build to static files are served from a CDN. The project inspection decides which one fits, and projects with a Dockerfile always run as containers. What each runtime needs:

• Node.js, Next.js and Express: runtime packages belong in dependencies, and the app must listen on PORT and bind to 0.0.0.0.
• Python (FastAPI, Django, Flask): a production server in requirements.txt and a start command, from a Procfile or one you confirm.
• Go: go.mod and go.sum at the project root, and the app reads PORT.
• Java (Spring Boot, Quarkus, Micronaut): the ./mvnw or ./gradlew wrapper in the project.

In a monorepo, the agent asks which project to deploy; see monorepo for AI-assisted coding. For a website that builds to static files, the steps after setup are the same as in Deploy a website. For an API that only your other apps call, ask for a private app, a container with no public address; see Private services.

ProductEcho flags deploys, environment updates, pauses and deletes as destructive, and Cursor asks before running an MCP tool by default, so you see each one before it runs. Three habits make that review count:

• Read the prompt for deploy_application, update_application_env and any tool whose name starts with delete_. The sign-in grants write access, and that includes deleting apps and databases.
• If you set Cursor to run tools without asking, keep deploys, environment updates and deletes out of that list. Reads such as get_workspace_info, list_applications and get_application_status are the safe ones to allow.
• Keep secrets out of the code. The upload skips .env files, so set values as environment variables and let the agent read them back with sensitive values masked.

To go back to an earlier version, ask the agent to redeploy that version of your code.

ProductEcho does not show up in Cursor

Check that mcp.json is valid JSON, with no trailing comma, then restart Cursor. To see what Cursor reports, open the Output panel (Cmd+Shift+U on a Mac, Ctrl+Shift+U on Windows and Linux) and choose "MCP Logs" from the dropdown.

The sign-in does not finish, or the tools say unauthorized

The server answers 401 until you approve access in the browser window. Finish that step, then check "MCP Logs" if the server still shows as not connected. If it stays stuck, remove the ProductEcho entry, save, add it again and repeat the sign-in.

Cursor says the server is blocked

On a Cursor team plan, admins can restrict which MCP servers are allowed. Ask an admin to allow https://api.productecho.com/mcp.

The skills are missing

Check that ~/.agents/skills/productecho-deploy exists, run the install command again if it does not, then restart Cursor and type / in Agent chat.

The deploy finished but the URL shows an error

Ready means the container started, not that your routes work. A gateway error usually means the app listens on the wrong port: it must bind to 0.0.0.0 and read the PORT variable. Ask the agent to check the port and redeploy, or follow why a deployment returns 502.

A Python deploy was refused

Without a Procfile, a Python app needs a start command. The agent proposes one from your code and asks you to confirm it before deploying.