Skip to main content
Glama

The Deployer for AI coding tools

Skills, a Claude Code plugin, a Cursor plugin and an MCP server that let your coding agent:

  • check whether a repository will deploy, and fix what's missing

  • deploy it into your own AWS, Google Cloud, Azure or DigitalOcean account end to end, with HTTPS, health checks and monitoring, asking you before anything that costs money

  • fix a failed deployment, in your code when that's the cause, and retry

  • run it afterwards: redeploys, env, domains, scaling, start and stop schedules, databases and access

  • move an app off Heroku, Railway, Render or Vercel, with the old app kept as the rollback

Your cloud provider bills you directly, and your first app is free.

Skills

Skill

Use it when

check-deploy-readiness

"Will this deploy?", "Is this production ready?", or before going live

deploy-to-own-cloud

"Deploy this", "Host this in my own AWS or DigitalOcean"

fix-failed-deployment

"My deploy failed", "Why won't it start?"

operate-live-app

"Add my domain", "Scale it up", "Stop it at night", "Attach a database"

migrate-off-platform

The repository has a Procfile, app.json, render.yaml, railway.json or railway.toml, or you're leaving a platform

Related MCP server: thedeployer

Install

Any agent the skills CLI supports (Claude Code, Cursor, Codex, GitHub Copilot, Gemini, Cline, Windsurf and more):

npx skills add Avinash147-1193/thedeployer-plugins

Claude Code plugin (skills plus the MCP server):

claude plugin marketplace add Avinash147-1193/thedeployer-plugins
claude plugin install thedeployer@thedeployer

Cursor: install The Deployer from the Cursor marketplace. To try it locally first, copy this folder to ~/.cursor/plugins/local/thedeployer and restart Cursor.

Gemini CLI:

gemini extensions install https://github.com/Avinash147-1193/thedeployer-plugins

The MCP server

check_repo and guide work without a key.

For everything else:

  1. Create an API key on your Profile page in The Deployer. Choose Operate to let the agent set up, launch and run projects, or Look and redeploy.

  2. Set it as THEDEPLOYER_API_KEY in your environment. Never put the key in a file you commit.

A key can't read your cloud credentials, your env values or billing, and anything that costs money waits for your yes.

Codex (~/.codex/config.toml):

[mcp_servers.thedeployer]
command = "npx"
args = ["-y", "thedeployer-mcp"]
env = { THEDEPLOYER_API_KEY = "your key" }

Privacy

For a local repository, thedeploy-check sends a git archive of the committed files to The Deployer's check service:

  • Who can see it: only that run.

  • How long it's kept: the archive is deleted when the check finishes, and the report after seven days.

  • What it never sends: uncommitted changes, ignored files or git history.

For a public repository, only its address is sent.

License

MIT

Maintenance

ActivityMaintained
ResponsivenessNo issues

Related MCP Connectors

Related MCP Servers

  • A
    license
    Not graded
    quality
    A
    maintenance
    Enables AI agents to deploy code to any hosting provider by creating PRs, building, and verifying health checks, all from a single natural language command.
    33 npm
    1
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI assistants to deploy and manage hosted apps from git repos, read logs, add Postgres databases and domains, manage API keys and budgets, and send requests to 200+ AI models. Connects over remote Streamable HTTP with OAuth sign-in, so users need no API keys, installs, or local server.
    MIT
  • A
    license
    Not graded
    quality
    B
    maintenance
    Enables AI agents to build and deploy an app from a GitHub repository to a managed live server and then operate it — logs, captured errors, health checks, managed Postgres, secrets, custom domains, email authentication, and Stripe checkout links. It also exposes safe, read/write-labelled tools so agents can rebuild, start/stop, and inspect projects without ever editing source code.
    MIT