orkestr MCP

Created By

orkestr2 months ago

The orkestr MCP server gives AI agents full control of the orkestr deployment platform over the Model Context Protocol. From an MCP client an agent can create and manage projects from a GitHub, GitLab, Bitbucket, or Codeberg repo, spin up environments, trigger and roll back deployments, deploy and invoke serverless functions, provision and back up managed PostgreSQL and Redis add-ons, manage custom domains, and read live logs, build logs, metrics, and health, all on infrastructure that stays in the EU.

# deployment

# EU hosting

Overview Content Tools Comments

Overview

What is orkestr MCP?

orkestr MCP is a Model Context Protocol server for orkestr, the EU-hosted deployment platform. It lets large language models deploy and operate real applications, connecting a Git repo, building and shipping it, running serverless functions, provisioning managed databases, and reading logs and metrics, all through structured tool calls on infrastructure that stays in the EU.

How to use orkestr MCP?

Generate an API token in the orkestr console under Settings -> API, then point your MCP client (Claude Code, Claude Desktop, Cursor, Windsurf, or any MCP-compatible client) at https://api.orkestr.eu/api/mcp with the token sent as Authorization: Bearer <token>. No install step: it is a hosted, streamable-HTTP server. Your agent then has 72 tools for the full deploy lifecycle.

Key features of orkestr MCP?

Full deployment lifecycle from one server: projects, environments, deployments, rollbacks, logs, and health.
Serverless functions and managed PostgreSQL and Redis add-ons, created and operated in natural language.
EU-hosted and GDPR-friendly by default, with all infrastructure in EU data centers.
Scoped, per-token access so an agent only ever sees the tools its token permits.

Use cases of orkestr MCP?

Deploy an app or AI-generated project straight from a chat or agent.
CI/CD and ChatOps: trigger deploys, roll back, and read build logs from an agent.
Autonomous incident response: watch health, read logs, and redeploy.
Provision and back up databases, manage domains, and monitor usage.

FAQ from orkestr MCP?

Which clients work with orkestr MCP?

Any MCP-compatible client, including Claude Code, Claude Desktop, Cursor, and Windsurf.

How do I authenticate?

With an orkestr API token from Settings -> API, sent as a bearer credential. Tool access is scoped to what the token permits.

Is it free to use?

orkestr has a free Starter tier with API access (1 token); paid plans add more tokens and higher limits. The MCP server itself adds no extra cost.

Where is my data hosted?

In the EU (Germany and Finland). orkestr is GDPR-compliant by default.

Is there a sandboxes server too?

Yes. A separate sandboxes MCP server at https://api.orkestr.eu/api/sandboxes/mcp runs isolated, ephemeral EU Linux environments for agent-generated code.

Server Config

{
  "mcpServers": {
    "orkestr": {
      "command": "npx",
      "args": [
        "mcp-remote",
        "https://orkestr.eu/api/mcp",
        "--header",
        "Authorization: Bearer ork_your_token_here"
      ]
    }
  }
}

Recommend Servers

TraeBuild with Free GPT-4.1 & Claude 3.7. Fully MCP-Ready.

ChatWiseThe second fastest AI chatbot™

Serper MCP ServerA Serper MCP Server

Tavily Mcp

Y GuiA web-based graphical interface for AI chat interactions with support for multiple AI models and MCP (Model Context Protocol) servers.

EdgeOne Pages MCPAn MCP service designed for deploying HTML content to EdgeOne Pages and obtaining an accessible public URL.

Playwright McpPlaywright MCP server

Jina AI MCP ToolsA Model Context Protocol (MCP) server that integrates with Jina AI Search Foundation APIs.

AiimagemultistyleA Model Context Protocol (MCP) server for image generation and manipulation using fal.ai's Stable Diffusion model.

CursorThe AI Code Editor

Zhipu Web SearchZhipu Web Search MCP Server is a search engine specifically designed for large models. It integrates four search engines, allowing users to flexibly compare and switch between them. Building upon the web crawling and ranking capabilities of traditional search engines, it enhances intent recognition capabilities, returning results more suitable for large model processing (such as webpage titles, URLs, summaries, site names, site icons, etc.). This helps AI applications achieve "dynamic knowledge acquisition" and "precise scenario adaptation" capabilities.