Skip to content
MCP server

The Deployer

Deploy apps to your own AWS, GCP, Azure or DigitalOcean account from an AI agent

Install
Pricing
Open source
Platforms
API, CLI, Web
Runs
Locally or Remotely
Version
0.3.0
Listing updated
3 days ago

About The Deployer

The Deployer is an open-source MCP server for cloud and infrastructure. It can run locally on your machine or as a hosted remote server.

An agent connected to The Deployer reads a repository, shows an infrastructure plan with an estimated monthly cost, and launches only after you say yes. Deploys go into your own cloud account or onto a server you already pay for, such as a Hostinger or GoDaddy VPS or any Ubuntu or Debian machine. The site lists Hetzner as planned.

Tools run from a check-only mode up to operations. check_repo needs no key and reports what a public repo would need and cost on each cloud. With a key, plan_deploy, status, logs, diagnose and redeploy work, and create_project, set_env and launch need the Operate level. Env var values are never shown back, and logs have secrets removed. An agent cannot see cloud or git credentials, change billing or team settings, delete projects, databases or servers, or create keys.

Sign-in is by browser rather than a pasted key for Claude Code, Claude, Cursor, VS Code and Codex. The MCP server is MIT licensed. The site warns that current cloud connections use long-lived keys with broad permissions and recommends a dedicated cloud account; estimates are not spending caps.

Install

Run in a terminal

claude mcp add --transport http deployer https://app.thedploy.com/mcp

Add to Settings → Connectors → Add custom connector

https://app.thedploy.com/mcp
Install in CursorOpens Cursor, which asks you to confirm. Or add it by hand:

Add to ~/.cursor/mcp.json

{
  "mcpServers": {
    "deployer": {
      "url": "https://app.thedploy.com/mcp"
    }
  }
}
Install in VS CodeOpens VS Code, which asks you to confirm. Or add it by hand:

Add to .vscode/mcp.json

{
  "servers": {
    "deployer": {
      "type": "http",
      "url": "https://app.thedploy.com/mcp"
    }
  }
}

Add to ~/.codeium/windsurf/mcp_config.json

{
  "mcpServers": {
    "deployer": {
      "serverUrl": "https://app.thedploy.com/mcp"
    }
  }
}

Add to your client's MCP settings (most use this shape)

{
  "mcpServers": {
    "deployer": {
      "type": "http",
      "url": "https://app.thedploy.com/mcp"
    }
  }
}

Configuration

  • THEDEPLOYER_API_KEYA personal API key from your Profile page in The Deployer. Without it, only check_repo works.

Tools this server provides (14)

Taken from the project documentation; the running server may differ.

guide
Playbooks for agents.
check_repo
Checks whether a public repository will deploy.
plan_deploy
Check plus connected accounts and next step.
account
Connected clouds and key permissions.
status
Projects and latest deployments.
project
One project in depth.
deployment
Deployment state and fixes.
logs
Deployment log with secrets removed.
diagnose
Read-only checks on a live server.
redeploy
Pulls latest code and restarts.
create_project
Creates a project from a repository.
set_env
Sets environment variables.
launch
Shows plan and cost, then launches.
request_done_for_you
Requests a done-for-you Launch or Move.

What it does

Repo check
Reports whether a public repository will deploy and what it costs per cloud, with no key.
Plan and approve
Shows the plan and monthly estimate before anything is created.
Own-cloud deploys
Runs in your AWS, Google Cloud, Azure or DigitalOcean account or on your own server.
Live diagnostics
Read-only checks of containers, app logs, memory and disk on a live server.
Redeploy and env vars
Pulls the latest branch code and sets variables without revealing values.
Guarded actions
Cannot delete resources or touch billing, team or credentials.

Good for

  • Ask Claude Code to put a repository online in your own cloud
  • Preview hosting cost on several clouds before choosing
  • Redeploy after a push and read the deployment log
  • Diagnose a failing container on a VPS
  • Set environment variables without pasting them into chat

Pricing

Open source

MCP server is MIT licensed; platform plan prices not published; cloud costs billed by your provider.

Prices change. Check thedploy.com before you buy.

The Deployer FAQ

Can I try it without an account?

Yes, partly. Without a key only check_repo works, and it reports whether a public repository will deploy and its estimated cost.

Where does my app run?

In your own cloud account or server. The provider bills you directly; The Deployer plan covers the platform.

Can the agent delete things or change billing?

No. The README says an agent cannot delete projects, databases or servers, change billing, team or account settings, or create keys.

Which clients work?

Claude Code, Claude, Cursor, VS Code, Codex and other MCP clients, over stdio or streamable HTTP.

Is The Deployer free?

Yes. The Deployer is open source, so you can use and self-host it for free.

How do I add The Deployer to Claude Code?

Run this command in your terminal: claude mcp add --transport http deployer https://app.thedploy.com/mcp

What are the best alternatives to The Deployer?

The closest alternatives to The Deployer are REA, Codebase Memory, GitHub, Serena MCP: the IDE for your agent and XERJ.

Alternatives to The Deployer

  1. REA

    MCP server

    CLI and MCP server that lets coding agents reverse engineer apps and binaries

    Runs locally
    • Open source
    • 464K GitHub stars
    • Developer tools
  2. Codebase Memory

    MCP server

    Local MCP server that builds a code knowledge graph for AI coding agents

    Runs locally
    • Open source
    • 48.7K GitHub stars
    • Knowledge and memory
  3. GitHub

    MCP server

    Official MCP server connecting AI assistants to GitHub repos, issues and workflows

    Not checked yet
    • Remote
    • Open source
    • 34.5K GitHub stars
    • Developer tools
  4. MCP toolkit giving coding agents symbol-level code retrieval and editing

    Runs locally
    • Open source
    • 31.5K GitHub stars
    • Developer tools
  5. XERJ

    MCP server

    Local search engine for AI agents with cited answers over your code and docs

    Runs locally
    • Open source
    • 19.2K GitHub stars
    • Knowledge and memory
  6. Ouroboros

    MCP server

    Spec-first layer that pins requirements and verifies results of AI coding agent work

    Runs locally
    • Open source
    • 6.4K GitHub stars
    • Developer tools