mcpField
R
run.zero

run.zero

Remote
run-zero.deCloud & Infra0Updated today

About run.zero

run.zero is a Germany-hosted PaaS MCP server for teams that want an AI agent to manage apps, APIs, and Postgres. Its tools cover the path from pushing code and deploying services to monitoring them and restoring releases.

Key features

  1. 01Create and manage apps and services
  2. 02Push files and manage code
  3. 03Deploy apps and inspect build logs
  4. 04View logs and metrics, scale services
  5. 05Manage secrets, Postgres, and users
  6. 06Manage releases and versions

Use cases

  1. 01Have an agent deploy a web app or API
  2. 02Query an app's managed Postgres database
  3. 03Investigate build or runtime issues
  4. 04Restore an earlier application version

MCP support

The server uses Streamable HTTP and OAuth 2.1 with PKCE. Tool discovery is available without sign-in; tool calls require sign-in.

Configuration

Remote servers need no local install. Pick your client, then copy the config or install in one click.

Endpointhttps://api.run-zero.de/mcp
Copy install command
Claude CodeTerminal
Cursor.cursor/mcp.json
VS Code.vscode/mcp.json
Claude Desktopclaude_desktop_config.json
Windsurf~/.codeium/windsurf/mcp_config.json

Run commands in a terminal; paste JSON into the client’s MCP config and restart. Servers that need sign-in will prompt on first connect.

Tools

Details

From the project README

run.zero MCP server

Deploy web apps, APIs and Postgres databases straight from your AI agent. run.zero is a platform as a service by Get IT Done GmbH, hosted in Germany on European infrastructure.

  • Endpoint: https://api.run-zero.de/mcp (Streamable HTTP)
  • Sign-in: OAuth 2.1 with PKCE and dynamic client registration. No API key to copy.
  • Discovery: initialize and tools/list answer without sign-in, so you can see every tool first. Tool calls need sign-in.
  • Registry name: de.run-zero/mcp in the official MCP Registry

What your agent can do

AreaTools
Appsrunzero_create_app, runzero_list_apps, runzero_get_app, runzero_delete_app
Coderunzero_push_files (one atomic commit into a managed Git repo), runzero_list_files, runzero_read_file, runzero_upload_assets
Deployrunzero_deploy, runzero_wait_for_build, runzero_list_builds, runzero_get_build_logs, runzero_rebuild_service, runzero_deploy_preview
Runrunzero_get_logs, runzero_get_metrics, runzero_scale_service, runzero_add_service, runzero_delete_service
Configrunzero_set_secrets, runzero_list_secrets, runzero_delete_secret, runzero_describe_addon
Datarunzero_db_query against the app's managed Postgres
Releasesrunzero_list_releases, runzero_restore_release, runzero_list_versions, runzero_activate_version, runzero_publish
Login for your apprunzero_create_user, runzero_list_users, runzero_set_user_enabled, runzero_create_identity_provider and more (managed Keycloak realm per app)
Helprunzero_get_help (workflow, files, addons, procfile, domains)

The platform builds with buildpacks (Node.js, Python, Go, PHP, Java). The web process listens on $PORT. A run-zero.yaml declares several services and the addons postgres and keycloak. Every service gets https://<service>-<app>.run-zero.de with TLS, and custom domains get a Let's Encrypt certificate.

Connect

Claude Code
claude mcp add --transport http run-zero https://api.run-zero.de/mcp

Then run /mcp in Claude Code and sign in.

Claude Desktop and claude.ai

Settings, Connectors, Add custom connector, URL https://api.run-zero.de/mcp.

Cursor

~/.cursor/mcp.json:

{
  "mcpServers": {
    "run-zero": { "url": "https://api.run-zero.de/mcp" }
  }
}
VS Code
code --add-mcp '{"name":"run-zero","type":"http","url":"https://api.run-zero.de/mcp"}'
Gemini CLI
gemini extensions install https://github.com/getitdone-gmbh/run-zero-mcp

Try it

Ask your agent:

Create a run.zero app called hello, push a small Express server that listens on $PORT, deploy it and give me the URL.

Links

This repository only describes the hosted server. It does not contain its source code.

Comments

Markdown supported

New to MCP?

From what the protocol is to installing your first server, these answers cover most first questions.

An open protocol that defines how AI applications connect to external tools and data in a uniform way. Clients talk to the model; MCP servers provide tools, resources and prompt templates. They exchange standard messages, so one server can be reused by many clients.