Coolify
This MCP server provides complete Coolify API integration, enabling AI assistants to manage self-hosted applications, databases, services, and infrastructure through a unified interface. Built by Felix Allistar using TypeScript with auto-generated SDK from OpenAPI specifications, it offers dual-mode operation as both CLI tool and MCP server with comprehensive coverage of Coolify's deployment platform including 110+ one-click services (WordPress, Ghost, MinIO), 8 database types (PostgreSQL, MySQL, MongoDB, Redis), application lifecycle management, server connectivity validation, and environment variable handling. The implementation features automatic type generation with CI/CD pipeline for API updates, robust error handling with Zod validation, and smart entry point detection for seamless switching between CLI and MCP modes, making it valuable for DevOps workflows requiring infrastructure automation, self-hosted application management, and scenarios where AI assistants need to deploy and monitor containerized services across multiple servers.
Composite of vulnerability cleanliness, spec conformance, provenance, stability, and usage signals — scanned and weighted by Cognium. Human and agent signals are tracked separately.
View full trust & usage report →Metadata
- Version
- 1.0.0
- Skill type
- atomic
- Execution layer
- mcp-remote
- Category
- database
- Source
- PulseMCP
- Repository
- github.com/felixallistar/coolify-mcp
- Author type
- human
- Updated
- 2026-05-27
Use via MCP
Resolve Coolify from your agent
Streamable HTTP transport at https://api.skillsregistry.net/mcp. No auth for read tools. Discovery: .well-known/mcp.json.
One command in your shell — Claude Code wires it up and verifies the connection. Run /mcp in any session to confirm.
claude mcp add --transport http --scope user skillsregistry https://api.skillsregistry.net/mcp--scope user for --scope project to commit it to .mcp.json.