Works with the AI Agents you already use

    Claude CodeClaude CodeCursorCursorCodex CLICodex CLIMuseMuseDotsDots+21 more

    Coolify Read-only MCP

    1

    Read-only MCP interface for Coolify to inspect servers, applications, deployments, and logs via your AI agent.

    $29

    Secure checkout via Stripe

    Money-back guarantee

    Converts to your local currency at checkout

    Security scanned
    Coolify Read-only MCP

    Coolify Read-only MCP

    Example session with this skill installed

    List my servers and check the logs for the application with UUID 'a1b2c3d4'.

    • Read your context and instructions
    • Compiled the coolify read-only mcp

    I have retrieved the list of servers and the latest log entries for the requested application.

    Coolify Infrastructure Status

    Resource TypeName/IdentifierStatusDetails
    Serverproduction-node-01OnlineUbuntu 22.04, 4 vCPU, 8GB RAM
    Serverstaging-node-01OnlineUbuntu 22.04, 2 vCPU, 4GB RAM
    Applicationweb-frontend (a1b2c3d4)RunningLast deployed 2h ago

    Application Logs: web-frontend (a1b2c3d4)

    2023-10-27 14:20:01 INFO: Starting Next.js production build...
    2023-10-27 14:20:05 ERROR: ConnectionTimeoutError: Failed to connect to database at 10.0.0.5:5432
    2023-10-27 14:20:05 WARN: Retrying connection in 5 seconds (Attempt 1/5)
    2023-10-27 14:20:10 ERROR: ConnectionTimeoutError: Failed to connect to database at 10.0.0.5:5432
    2023-10-27 14:20:10 WARN: Retrying connection in 5 seconds (Attempt 2/5)
    

    Next steps

    1. Run coolify_list_service_databases for the service associated with this app to check DB health.
    2. Use coolify_get_server for 'production-node-01' to verify if there are any network connectivity issues.
    3. Inspect the staging environment to see if the database connection string differs.

    Connects securely to your tools. The creator never sees your data.

    About this skill

    Debugging Coolify infrastructure manually via the dashboard or SSH is slow when you need quick answers. This skill provides a read-only bridge to your Coolify instance via an MCP server, allowing you to query infrastructure state directly from your agent.

    What it does

    • Server Inspection lists all managed servers and retrieves detailed metadata for specific nodes.
    • Application Monitoring fetches lists of deployed applications and their current configurations.
    • Service & Database Auditing tracks services and their associated databases, including service-specific logs.
    • Deployment Tracking retrieves the status and history of recent deployment attempts across the fleet.
    • Log Retrieval streams application and service logs for rapid troubleshooting and error diagnosis.

    How it works

    1. Discovery starts with coolify_list_servers or coolify_list_applications to map out the environment.
    2. Identification captures the specific UUID of the target resource from the list results.
    3. Inspection invokes coolify_get_application or coolify_get_service using the UUID to see the full state.
    4. Diagnosis reads targeted log segments via coolify_application_logs to isolate issues.

    Frameworks & tools

    This skill requires a locally configured Coolify Read-only MCP server. It interfaces with the Coolify API to query servers, Docker-based applications, and managed services.

    Why this beats prompting it yourself

    Standard prompts cannot access your private infrastructure state or live logs. This skill provides the specific tool definitions and safety constraints required to browse your Coolify instance without risking accidental destructive actions or configuration changes.

    Use cases

    • Check the status of a failing deployment without opening the Coolify dashboard.
    • Audit database associations and resource allocations across multiple services.
    • Quickly scan application logs to identify the root cause of a 500 error.
    • Verify server health and resource availability before pushing new code.

    Known limitations

    This skill is strictly read-only and cannot perform deployments, restarts, or configuration changes. It requires the MCP server to be pre-configured with a valid API token.

    Strictly read-only; no support for restarts or configuration changes. Requires local MCP server configuration. Does not guarantee 100% redaction of secrets in logs.

    How to use

    1. 1

      Connect your agent to the Agensi MCP

      Copy the prompt and paste it into Claude, ChatGPT, Cursor or any agent that supports MCP. It sets up the connection for you. Manual setup

    2. 2

      Sign in to Agensi

      Your agent shows a sign-in link. Sign in and click Allow.

    3. 3

      Ask for what you need

      Your agent loads this skill and uses it on your task. It always asks before any payment.

    Reviews

    No reviews yet

    Be one of the first to try it. Every listed skill goes through the trust checks below.

    Security scanned

    Checked by our 8-point scan before listing

    Fresh listing

    Recently published to Agensi

    Money-back guarantee

    Doesn't do what its page promises? You get your money back.

    Trust & safety

    Security scan

    Security scan passed 1 month ago

    Requires

    Python

    Permissions

    Terminal / Shell
    Read Files
    Network Access
    Environment Variables
    Listed1 month ago

    What's inside

    Frequently Asked Questions

    This skill allows your AI agent to browse your Coolify infrastructure (servers, apps, and logs) in real-time, eliminating the need to manually toggle between the dashboard and your terminal during debugging sessions.

    The skill is built on the Model Context Protocol (MCP), meaning it is compatible with any AI agent or IDE that supports MCP, such as Claude Desktop or Cursor.

    No, this skill is strictly read-only; it can fetch logs and status updates but lacks the permissions to trigger deployments, delete resources, or modify your environment variables.

    You will need a locally running MCP server instance and a valid Read-Only API token generated from your Coolify dashboard to authenticate the connection.

    Yes, as long as your AI agent has access to the configured MCP server, it can query any application, service, or database managed by that specific Coolify instance.

    New in LLM Ops