The Coolify MCP Server provides comprehensive management of Coolify deployments with 100% API coverage, offering both MCP integration for AI editors and CLI commands for terminal usage.
Core Capabilities:
Applications (21 operations): Full lifecycle management including listing, creating (6 deployment types: public repos, private GitHub/GitLab, Dockerfile, Docker image, Docker Compose), updating, deleting, and control operations (start, stop, restart, logs). Includes environment variable management (list, create, update bulk/single, delete).
Services (14 operations): Deploy and manage 70+ one-click services (WordPress, Ghost, MinIO, etc.) with full lifecycle control, environment variable management, and service type queries.
Databases (13 operations): Create and manage 8 database types (PostgreSQL, MySQL, MariaDB, MongoDB, Redis, KeyDB, ClickHouse, Dragonfly) with complete lifecycle control.
Projects & Infrastructure: Manage projects (list, create, update, delete) and their environments/resources. Server management includes creation, validation, domain management, and resource monitoring.
Deployments: List all or application-specific deployments, view deployment details, and trigger new deployments with custom parameters.
Private Keys: Full management for secure repository access (list, create, update, delete).
System Administration: Monitor system health and version, enable/disable API access, view system resources, and check configuration status.
Utilities: Connectivity testing (ping) and configuration validation.
Key Features: Identical functionality through both MCP tools and CLI commands, automated API updates to stay current with Coolify.
Supports creating and managing ClickHouse databases within Coolify deployments
Enables one-click deployment and management of Ghost CMS instances through Coolify
Supports application deployment from GitHub repositories via Coolify
Provides tools for creating and managing MariaDB databases in Coolify environments
Enables deployment and management of MinIO object storage services through Coolify
Supports creation and management of MongoDB databases within Coolify deployments
Provides tools for creating and managing MySQL databases in Coolify environments
Enables creation and management of PostgreSQL databases through Coolify
Supports creation and management of Redis databases in Coolify deployments
Enables one-click deployment and management of WordPress instances through Coolify
Click on "Deploy Server".
Wait a few minutes for the server to deploy. Once ready, it will show a "Started" state.
In the chat, type @ followed by the MCP server name and your instructions, e.g., "@Coolify MCP Server list my applications and show their current status"
That's it! The server will respond to your query, and you can continue using it as needed.
Here is a step-by-step guide with screenshots.
DEPERECATED USE THE SKILL NOW: https://github.com/FelixAllistar/coolify-manager
A Model Context Protocol (MCP) server for managing Coolify deployments, providing both programmatic MCP tools and comprehensive CLI commands.
MCP (Model Control Protocol) lets you manage Coolify directly from your AI editor.
For Cursor:
Add to ~/.cursor/mcp.json or <project_folder>/.cursor/mcp.json:
{
"mcpServers": {
"coolify-mcp": {
"command": "npx",
"args": ["-y", "@felixallistar/coolify-mcp", "--server"],
"env": {
"COOLIFY_API_URL": "https://your-coolify-instance.com",
"COOLIFY_API_TOKEN": "your-coolify-api-token"
}
}
}
}For VS Code:
Add to <project_folder>/.vscode/mcp.json:
{
"servers": {
"coolify-mcp": {
"command": "npx",
"args": ["-y", "@felixallistar/coolify-mcp", "--server"],
"env": {
"COOLIFY_API_URL": "https://your-coolify-instance.com",
"COOLIFY_API_TOKEN": "your-coolify-api-token"
},
"type": "stdio"
}
}
}🔑 Replace
your-coolify-instance.comwith your actual Coolify URL andyour-coolify-api-tokenwith your API token from Coolify Settings > API.
Open Cursor Settings (Ctrl+Shift+J) ➡ Click on MCP tab ➡ Enable coolify-mcp with the toggle
In your AI chat, try commands like:
List my Coolify applications
Create a new WordPress service called "my-blog"
Deploy my app with ID "app-123"
Show me all available database types# Install globally for CLI usage
npm install -g @felixallistar/coolify-mcp
# Test the installation
coolify-mcp --helpCreate a .env file in your project directory:
# Required: Your Coolify instance URL (include port if needed)
COOLIFY_API_URL=https://your-coolify-instance.com
# Required: Your Coolify API token (generate in Coolify Settings > API)
COOLIFY_API_TOKEN=your-coolify-api-token# Application management
coolify-mcp apps list
coolify-mcp apps create-public --name "my-app" --repository "https://github.com/user/repo" --project "project-id"
coolify-mcp apps start app-id
# Service management (70+ one-click services)
coolify-mcp services types
coolify-mcp services create --name "my-blog" --type "wordpress-with-mysql" --project "project-id"
# Database management (8 database types)
coolify-mcp databases create-postgresql --name "main-db" --project "project-id"
coolify-mcp databases create-redis --name "cache" --project "project-id"
# Project management
coolify-mcp projects list
coolify-mcp projects create --name "My Project"
# Test connectivity
coolify-mcp system healthRelated MCP server: Coolify MCP Server
Complete application lifecycle management with 6 deployment types, environment variables, logs, and control operations.
70+ one-click services including WordPress, Ghost, MinIO, and more with full environment management.
8 database types: PostgreSQL, MySQL, MariaDB, MongoDB, Redis, KeyDB, ClickHouse, Dragonfly.
Complete infrastructure management including private keys, system administration, and deployment monitoring.
This package provides two interaction methods with complete feature parity:
🤖 MCP Tools: For AI agents and Cursor integration (recommended)
💻 CLI Commands: For direct terminal usage
Both interfaces provide identical functionality - choose based on your workflow.
Stay in sync with Coolify's latest API:
npm run refresh # Download latest API spec and rebuild
npm run check-updates # Check for API changesgit clone https://github.com/FelixAllistar/coolify-mcp.git
cd coolify-mcp
npm install
npm run refresh
npm run dev✅ 100% Coolify API Coverage - Applications, Services, Databases, Projects, Servers, Deployments, Private Keys, System Administration
GLWTPL (Good Luck With That Public License) - see LICENSE file for details.
This software might just work or not, there is no third option. Good luck and Godspeed.
{
"mcpServers": {
"coolify-mcp": {
"command": "npx",
"args": ["-y", "@felixallistar/coolify-mcp", "--server"],
"env": {
"COOLIFY_API_URL": "https://your-coolify-instance.com",
"COOLIFY_API_TOKEN": "your-coolify-api-token"
}
}
}
}{
"mcpServers": {
"coolify-mcp": {
"command": "node",
"args": ["node_modules/@felixallistar/coolify-mcp/dist/index.js", "--server"],
"env": {
"COOLIFY_API_URL": "https://your-coolify-instance.com",
"COOLIFY_API_TOKEN": "your-coolify-api-token"
}
}
}
}npm install -g @felixallistar/coolify-mcpThen use the MCP server binary:
{
"mcpServers": {
"coolify-mcp": {
"command": "coolify-mcp",
"env": {
"COOLIFY_API_URL": "https://your-coolify-instance.com",
"COOLIFY_API_TOKEN": "your-coolify-api-token"
}
}
}
}For CLI commands, simply add arguments to the coolify-mcp command:
# Using npx (no installation needed)
npx @felixallistar/coolify-mcp --help
npx @felixallistar/coolify-mcp apps list
# Or install globally for easier CLI usage
npm install -g @felixallistar/coolify-mcp
coolify-mcp --help
coolify-mcp apps list| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform | |
| id | No | Application UUID | |
| env_id | No | Environment variable ID | |
| body | No | JSON request body |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
No parameters | |||
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform | |
| id | No | Database UUID | |
| body | No | JSON request body |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform | |
| id | No | Deployment UUID | |
| applicationUuid | No | Application UUID (for list_by_app operation) | |
| query | No | JSON query parameters for deploy operation |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| random_string | No | Dummy parameter for no-parameter tools |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform | |
| id | No | Private Key UUID | |
| body | No | JSON request body |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform | |
| id | No | Project UUID | |
| environmentNameOrUuid | No | Environment name or UUID (for environment operation) | |
| body | No | JSON request body |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform | |
| id | No | Server UUID | |
| body | No | JSON request body |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform | |
| id | No | Service UUID | |
| env_id | No | Environment variable UUID | |
| body | No | JSON request body |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
| Name | Required | Description | Default |
|---|---|---|---|
| operation | Yes | Operation to perform |
Does the description disclose side effects, auth requirements, rate limits, or destructive behavior?
Tool has no description.
Agents need to know what a tool does to the world before calling it. Descriptions should go beyond structured annotations to explain consequences.
Is the description appropriately sized, front-loaded, and free of redundancy?
Tool has no description.
Shorter descriptions cost fewer tokens and are easier for agents to parse. Every sentence should earn its place.
Given the tool's complexity, does the description cover enough for an agent to succeed on first attempt?
Tool has no description.
Complex tools with many parameters or behaviors need more documentation. Simple tools need less. This dimension scales expectations accordingly.
Does the description clarify parameter syntax, constraints, interactions, or defaults beyond what the schema provides?
Tool has no description.
Input schemas describe structure but not intent. Descriptions should explain non-obvious parameter relationships and valid value ranges.
Does the description clearly state what the tool does and how it differs from similar tools?
Tool has no description.
Agents choose between tools based on descriptions. A clear purpose with a specific verb and resource helps agents select the right tool.
Does the description explain when to use this tool, when not to, or what alternatives exist?
Tool has no description.
Agents often have multiple tools that could apply. Explicit usage guidance like "use X instead of Y when Z" prevents misuse.
Recent tool additions, removals, and schema changes observed during successful MCP inspections.
applicationsconfig-statusdatabasesdeploymentspingprivate-keysprojectsserversservicessystemScored across 10 tools
The tool names identify broad resource areas, but several overlap conceptually, such as services vs. applications and system vs. config-status. With no descriptions, agents have little basis to determine which tool is appropriate for a given task.
Most tool names follow a simple lowercase-hyphenated plural noun pattern, but there is no consistent verb-noun structure and there are outliers like ping, system, and config-status. The naming is readable but not a strong unified convention.
Ten tools is a reasonable count for a server focused on managing infrastructure resources. However, the lack of descriptions makes it difficult to confirm that each tool earns its place in the set.
The surface appears to be read-oriented resource access rather than full lifecycle coverage, with no obvious create, update, or delete operations. Tools like private-keys and config-status hint at configuration management, but the set likely leaves agents unable to perform common management workflows.
Deploy and manage your apps, databases, storage, and scheduled jobs from your AI agent
Deploy and manage applications, databases, domains, and git repos
Build, validate, deploy — HTTP APIs, cron jobs, webhooks and MCP tools — from your AI client.
Deploy and manage Jade Hosting projects from AI clients. Jade account and OAuth required.
