Ansible Tower MCP server

Bridges AI systems with Ansible Tower/AWX instances for infrastructure automation, enabling inventory, host, job template, and credential management through a secure API interface for DevOps workflows.
Back to servers
Provider
Forge
Release date
Mar 16, 2025
Language
Python
Stats
3 stars

This MCP server enables Large Language Models (LLMs) to interact with Ansible Tower, allowing automation via natural language conversations. It implements the Model Context Protocol to create a bridge between AI models and your Ansible infrastructure.

Prerequisites

Before installing the MCP server, ensure you have:

  • An Ansible Tower instance with admin access
  • Python 3.8 or higher
  • Access credentials for your Ansible Tower

Installation

Clone the Repository

git clone https://github.com/username/ansible-tower-mcp-server.git
cd ansible-tower-mcp-server

Set Up Environment

  1. Create a .env file based on the template:
cp .env.template .env
  1. Edit the .env file with your Ansible Tower credentials:
TOWER_HOST=https://your-tower-instance.example.com
TOWER_USERNAME=your_username
TOWER_PASSWORD=your_password
TOWER_VERIFY_SSL=false  # Set to true in production

Install Dependencies

pip install -r requirements.txt

Running the Server

Start the MCP server with:

python server.py

By default, the server runs on port 8000. You can specify a different port:

python server.py --port 8080

Using with LLM Providers

Configuration

When setting up your LLM provider, configure it to use the MCP protocol with your server URL:

MCP_SERVER_URL=http://localhost:8000

Available Commands

The MCP server exposes several Ansible Tower functions:

  • List Job Templates: Retrieves all available job templates
  • Run Job Template: Executes a specific job template
  • Check Job Status: Monitors the progress of running jobs
  • List Inventories: Shows available inventory resources
  • View Job Output: Retrieves the output from completed jobs

Example Interactions

When interacting with an LLM that supports MCP, you can use natural language to:

"List all available job templates in Ansible Tower"
"Run the 'Deploy Application' job template"
"Check the status of job ID 123"
"Show me the output from the last deployment job"

Troubleshooting

Common Issues

  • Connection Errors: Verify your Ansible Tower URL and credentials in the .env file
  • Authentication Failures: Ensure your user has sufficient permissions in Tower
  • SSL Verification: If you encounter SSL issues, try setting TOWER_VERIFY_SSL=false (not recommended for production)

Logs

Check the server logs for detailed error messages:

tail -f mcp_server.log

How to add this MCP server to Cursor

There are two ways to add an MCP server to Cursor. The most common way is to add the server globally in the ~/.cursor/mcp.json file so that it is available in all of your projects.

If you only need the server in a single project, you can add it to the project instead by creating or adding it to the .cursor/mcp.json file.

Adding an MCP server to Cursor globally

To add a global MCP server go to Cursor Settings > MCP and click "Add new global MCP server".

When you click that button the ~/.cursor/mcp.json file will be opened and you can add your server like this:

{
    "mcpServers": {
        "cursor-rules-mcp": {
            "command": "npx",
            "args": [
                "-y",
                "cursor-rules-mcp"
            ]
        }
    }
}

Adding an MCP server to a project

To add an MCP server to a project you can create a new .cursor/mcp.json file or add it to the existing one. This will look exactly the same as the global MCP server example above.

How to use the MCP server

Once the server is installed, you might need to head back to Settings > MCP and click the refresh button.

The Cursor agent will then be able to see the available tools the added MCP server has available and will call them when it needs to.

You can also explictly ask the agent to use the tool by mentioning the tool name and describing what the function does.

Want to 10x your AI skills?

Get a free account and learn to code + market your apps using AI (with or without vibes!).

Nah, maybe later