coolify-mcp
MCP server for Coolify — 42 optimized tools for managing self-hosted PaaS through AI assistants
No outside reports on file
This tool gives your AI assistant full control over your self-hosted applications, so only use it with trusted AI instances, strong API credentials, and careful monitoring of what it does.
Based on public adoption and transparency signals as of Oct 22, 2026. Our opinion, not a code audit or security guarantee.
What it can access
- Local filesNo local folder access notedLOW
- Command executionNo shell command runner notedLOW
- Network reachConnects to outside service APINOTED
- CredentialsRequires API key or tokenREVIEW
- Package sourcenpm (@masonator/coolify-mcp)PUBLIC
Inferred from this listing’s public package details and description. Check the project’s source before installing.
Install
npx -y @masonator/coolify-mcpEverything known
We found nothing about this project in the sources we read (last checked 2026-10-30). That does not mean it has no problems.
0 incidents · 0 advisories · 0 news articles · 0 community threads · checked 2026-10-30
Popularity grade: B (from public signals such as stars and downloads, not a code review). Graded 2026-10-22.
Sources we read: OSV, GitHub Advisory Database, CISA Known Exploited Vulnerabilities, 44 security news feeds and our incident library. Last checked 2026-10-30.
About Coolify MCP
This is an MCP server that connects AI assistants to Coolify, a self-hosted platform for deploying and managing applications. It provides 42 tools to let Claude or other AI helpers control deployments, manage services, and handle infrastructure through natural language commands.
Who it’s for
Developers who use Coolify for self-hosted application deployments and want AI assistants to help manage their infrastructure. Teams running private cloud setups who need automated deployment and service management.
Alternatives
- Dokploy MCP: Another self-hosted deployment platform with AI connector support.
- CapRover integrations: Alternatives for managing containerized applications through automation.
- Ansible AWX connectors: Infrastructure-as-code tools with AI integration for deployment management.
Setup
Check these steps against the project’s own instructions before running anything.
Install via npm: npm install @masonator/coolify-mcp
Or add to Claude Desktop config at ~/.config/Claude/claude_desktop_config.json:
{
"mcpServers": {
"coolify-mcp": {
"command": "npx",
"args": ["-y", "@masonator/coolify-mcp"]
}
}
}
Follow the project's README for API key setup and Coolify instance connection details.
Why this grade
Signal-based grade (4/7 points): well starred on GitHub, listed in several sources, public source code. This reflects adoption and transparency, not a code review.
Popularity and upkeep
- GitHub stars
- 618
- Listing last refreshed
- 2026-10-30
These are public popularity signals, not a maintenance check. Look at the repository’s commit history and open issues.
Risks to watch for
- Full infrastructure access: The tool can deploy, delete, and modify applications and services on your Coolify instance, so compromised credentials expose your entire deployment system.
- Credential handling: API keys and authentication tokens needed to reach Coolify could be leaked if the connector logs, caches, or mishandles them.
- Prompt injection: Attackers could craft deployment requests through the AI that trigger unintended infrastructure changes if input validation is weak.
- Data exposure: Logs and error messages from deployments might expose sensitive information about your services, configurations, or environment variables.
- Limited adoption signal: Only 616 GitHub stars and zero npm downloads suggest minimal real-world use and testing, so undiscovered bugs are likely.
How to lower the risk
Least-privilege permissions
- Create a Coolify API user with minimal required permissions, not full admin access.
- Rotate API keys regularly and use separate credentials for this connector.
Network isolation
- Run the MCP server on a private network segment if possible, not exposed to the internet.
- Restrict which AI assistants can access this connector to trusted applications only.
Monitoring
- Log all connector activity and infrastructure changes it triggers for audit trails.
- Set up alerts for unexpected deployments, deletions, or configuration modifications.
Red flags to watch for
- Unusual deployment attempts or service changes you didn't request through the AI.
- Errors mentioning credential failures, authentication issues, or API errors.
- Performance slowdowns or failed connections suggesting the connector is unstable.
Questions
How do I install Coolify MCP?
Run npx -y @masonator/coolify-mcp in your terminal, or add the server entry to your claude_desktop_config.json or .cursor/mcp.json as shown in the Setup section on this page. Full setup docs and environment variables are in github.com/StuMason/coolify-mcp.
Are there security reports about Coolify MCP?
No reports found for this package in our research (last checked 2026-10-30). Coolify MCP currently holds Grade B (Some risk signals) based on public adoption and transparency signals. Key risk areas to watch include full infrastructure access, credential handling, prompt injection.
Is Coolify MCP actively maintained?
Coolify MCP has 618 GitHub stars. Our directory data was last refreshed on 2026-10-30. Check recent commit activity, release tags, and open issues at github.com/StuMason/coolify-mcp before pinning it in production.
What are alternatives to Coolify MCP?
Notable alternatives to Coolify MCP include Dokploy MCP (Another self-hosted deployment platform with AI connector support), CapRover integrations (Alternatives for managing containerized applications through automation), Ansible AWX connectors (Infrastructure-as-code tools with AI integration for deployment management). You can also compare Coolify MCP side by side with other MCP servers in the Related tools section on this page.
Key facts
- Type
- App connector
- Publisher
- StuMason
- Source code
- github.com/StuMason/coolify-mcp
- Install command
- npm install @masonator/coolify-mcp
- Est. context load
- ~850 tokens / turn (~5 tool schemas, 0.43% of 200k context)
- Popularity
- 618 GitHub stars
- Last updated
- 2026-10-30
- Last graded
- 2026-10-22
Community
Discussions for Coolify MCP
Ask questions or share configuration tips. Governed by our Community Rules & Terms.
No posts match this filter yet.
Be the first to ask a question or share a working tip.
Check before you install, in Claude
Your assistant answers Block, Review or No known issues for any package before it installs it.
Get this check inside Claude