Installation¶

postiz-agent is a standard Python package and a prebuilt container image. Choose the path that matches how you intend to run it.

Requirements¶

Python 3.11 – 3.14.
A reachable Postiz instance and an API token — use the managed service at postiz.com or deploy your own (see Backing Platform).

From PyPI (recommended)¶

pip install postiz-agent

Optional extras¶

The base install ships the MCP server runtime. Install an extra for additional capability:

Extra	Install	Pulls in
(base)	`pip install postiz-agent`	FastMCP MCP-server runtime (`agent-utilities[mcp]`)
`agent`	`pip install "postiz-agent[agent]"`	Pydantic-AI agent server + Logfire tracing
`all`	`pip install "postiz-agent[all]"`	MCP server, agent server, and Logfire tracing
`test`	`pip install "postiz-agent[test]"`	`pytest`, `pytest-asyncio`, `pytest-cov`, `pytest-xdist`

# Typical: run both the MCP server and the A2A agent
pip install "postiz-agent[all]"

From source¶

git clone https://github.com/Knuckles-Team/postiz-agent.git
cd postiz-agent
pip install -e ".[all]"          # editable install with every extra

With uv:

uv pip install -e ".[all]"
uv run postiz-mcp

Prebuilt Docker image¶

A multi-stage, slim image is published on every release (entrypoint postiz-mcp):

docker pull knucklessg1/postiz-agent:latest

docker run --rm -i \
  -e POSTIZ_URL=https://api.postiz.com/public/v1 \
  -e POSTIZ_TOKEN=your_postiz_token \
  knucklessg1/postiz-agent:latest        # stdio transport (default)

For an HTTP server with a published port and the agent server, see Deployment.

Verify the install¶

postiz-mcp --help
python -c "import postiz_agent; print(postiz_agent.__version__)"

Next steps¶

Deployment — run it as a long-lived MCP and agent server behind Caddy + DNS.
Usage — call the tools, the API, and the CLI.
Configuration — every environment variable.