Manage Coolify deployments and infrastructure via API calls in your AI chat. For developers integrating Coolify automation into Claude or other LLM workflows.
io.github.frndchagas/coolify-mcp
Local install
STDIO
2 required env vars
How models use it and what it is built for.
Manage Coolify deployments and infrastructure via API calls in your AI chat. For developers integrating Coolify automation into Claude or other LLM workflows.
Local install — runs as a subprocess.
Configuration this server reads at startup.
Coolify API base URL.
Coolify API token.
Fail on version mismatch.
Enable write operations.
Override OpenAPI version ref (optional).
Where to find authoritative docs and source for Coolify.
Paste any of these into Agent Studio after connecting Coolify.
Common questions about connecting and running Coolify.
What is the Coolify MCP server?
It's an MCP server that exposes Coolify's API operations to AI assistants, letting you query and manage deployments, projects, and infrastructure through natural language. You connect it by providing your Coolify API token and base URL.
How do I authenticate with Coolify?
Set two required environment variables: COOLIFY_BASE_URL (your Coolify instance URL) and COOLIFY_TOKEN (your API token from Coolify). Optionally set COOLIFY_ALLOW_WRITE=true to enable deployment and modification operations.
Can I use this to deploy applications?
Yes, but only if you set the COOLIFY_ALLOW_WRITE environment variable to true. By default, the server runs in read-only mode to prevent accidental changes.
What happens if my Coolify API version doesn't match?
By default, the server will warn on version mismatches. Set COOLIFY_STRICT_VERSION=true to fail immediately if your Coolify instance version differs from the server's expected version.
How do I install and run this MCP server?
Run `npx @fndchagas/coolify-mcp@0.1.4` after setting your environment variables. The server communicates via stdio, so configure your AI client (Claude, etc.) to spawn it as a subprocess with the required env vars.
MCP Playground runs 10,000+ hosted MCP servers — GitHub, Linear, Notion, Stripe, Sentry and more — across Claude, GPT, Gemini, DeepSeek and 60+ AI models. Compare model answers side-by-side, save agent presets, share runs. Zero install.
Open Agent StudioJudges Panel
45 judges that evaluate AI-generated code for security, cost, and quality with built-in AST.
Addozhang Nexus
Query Sonatype Nexus Repository (OSS/Pro) for Maven, Python, and Docker artifacts
Cyanheads MCP Ts Template
TypeScript template for building MCP servers with declarative tooling, observability, and auth.
Chernistry Bernstein
Declarative agent orchestration for engineering teams