Installation¶
ansible-tower-mcp is a standard Python package and a prebuilt container image.
Pick the path that matches how you want to run it.
Requirements¶
- Python 3.11 – 3.14.
- A reachable Ansible Tower / AWX controller (Ansible Automation Platform) with API access — see the Backing Service note for connection guidance.
From PyPI (recommended)¶
Optional extras¶
The base install is intentionally minimal. Install the extra for what you need:
| Extra | Install | Pulls in |
|---|---|---|
mcp |
pip install "ansible-tower-mcp[mcp]" |
FastMCP MCP-server runtime (agent-utilities[mcp]) |
agent |
pip install "ansible-tower-mcp[agent]" |
Pydantic-AI agent server + Logfire tracing |
all |
pip install "ansible-tower-mcp[all]" |
Everything above (MCP + agent + Logfire) |
test |
pip install "ansible-tower-mcp[test]" |
pytest, pytest-asyncio, pytest-cov, pytest-xdist |
From source¶
git clone https://github.com/Knuckles-Team/ansible-tower-mcp.git
cd ansible-tower-mcp
pip install -e ".[all]" # editable install with every extra
With uv:
Prebuilt Docker image¶
A multi-stage, slim image is published on every release (entrypoint
ansible-tower-mcp):
docker pull knucklessg1/ansible-tower-mcp:latest
docker run --rm -i \
-e ANSIBLE_BASE_URL=https://your-tower.example.com \
-e ANSIBLE_USERNAME=admin \
-e ANSIBLE_PASSWORD=secret \
knucklessg1/ansible-tower-mcp:latest # stdio transport (default)
For an HTTP server with a published port and the agent server, see Deployment.
Verify the install¶
Next steps¶
- Deployment — run it as a long-lived MCP / agent server behind Caddy + DNS.
- Usage — call the tools, the
Apiclient, and the CLI. - Configuration — every environment variable.