Skip to main content

Agent for interacting with Postiz Public API

Project description

Postiz Agent - A2A | AG-UI | MCP

PyPI - Version MCP Server PyPI - Downloads GitHub Repo stars GitHub forks GitHub contributors PyPI - License GitHub

GitHub last commit (by committer) GitHub pull requests GitHub closed pull requests GitHub issues

GitHub top language GitHub language count GitHub repo size GitHub repo file count (file type) PyPI - Wheel PyPI - Implementation

Version: 0.9.0

Overview

Postiz Agent MCP Server + A2A Agent

Agent for interacting with Postiz Public API

This repository is actively maintained - Contributions are welcome!

MCP

Using as an MCP Server

The MCP Server can be run in two modes: stdio (for local testing) or http (for networked access).

Environment Variables

  • POSTIZ_URL: The URL of the target service.
  • POSTIZ_TOKEN: The API token or access token.

Run in stdio mode (default):

export POSTIZ_URL="http://localhost:8080"
export POSTIZ_TOKEN="your_token"
postiz-mcp --transport "stdio"

Run in HTTP mode:

export POSTIZ_URL="http://localhost:8080"
export POSTIZ_TOKEN="your_token"
postiz-mcp --transport "http" --host "0.0.0.0" --port "8000"

A2A Agent

Run A2A Server

export POSTIZ_URL="http://localhost:8080"
export POSTIZ_TOKEN="your_token"
postiz-agent --provider openai --model-id gpt-4o --api-key sk-...

Docker

Build

docker build -t postiz-agent .

Run MCP Server

docker run -d \
  --name postiz-agent \
  -p 8000:8000 \
  -e TRANSPORT=http \
  -e POSTIZ_URL="http://your-service:8080" \
  -e POSTIZ_TOKEN="your_token" \
  knucklessg1/postiz-agent:latest

Deploy with Docker Compose

services:
  postiz-agent:
    image: knucklessg1/postiz-agent:latest
    environment:
      - HOST=0.0.0.0
      - PORT=8000
      - TRANSPORT=http
      - POSTIZ_URL=http://your-service:8080
      - POSTIZ_TOKEN=your_token
    ports:
      - 8000:8000

Configure mcp.json for AI Integration (e.g. Claude Desktop)

{
  "mcpServers": {
    "postiz": {
      "command": "uv",
      "args": [
        "run",
        "--with",
        "postiz-agent",
        "postiz-mcp"
      ],
      "env": {
        "POSTIZ_URL": "http://your-service:8080",
        "POSTIZ_TOKEN": "your_token"
      }
    }
  }
}

Install Python Package

python -m pip install postiz-agent
uv pip install postiz-agent

Repository Owners

GitHub followers GitHub User's stars

MCP Configuration Examples

1. Standard IO (stdio) Deployment

{
  "mcpServers": {
    "postiz-agent": {
      "command": "uv",
      "args": [
        "run",
        "postiz-mcp"
      ],
      "env": {
        "AGENT_DESCRIPTION": "<YOUR_AGENT_DESCRIPTION>",
        "AGENT_SYSTEM_PROMPT": "<YOUR_AGENT_SYSTEM_PROMPT>",
        "ANALYTICSTOOL": "True",
        "DEFAULT_AGENT_NAME": "<YOUR_DEFAULT_AGENT_NAME>",
        "INTEGRATIONSTOOL": "True",
        "NOTIFICATIONSTOOL": "True",
        "POSTIZ_AGENT_VERIFY": "<YOUR_POSTIZ_AGENT_VERIFY>",
        "POSTIZ_TOKEN": "<YOUR_POSTIZ_TOKEN>",
        "POSTIZ_URL": "<YOUR_POSTIZ_URL>",
        "POSTSTOOL": "True",
        "UPLOADSTOOL": "True",
        "VIDEOTOOL": "True"
      }
    }
  }
}

2. Streamable HTTP (SSE) Deployment

{
  "mcpServers": {
    "postiz-agent": {
      "command": "uv",
      "args": [
        "run",
        "postiz-mcp",
        "--transport",
        "http",
        "--host",
        "0.0.0.0",
        "--port",
        "8000"
      ],
      "env": {
        "AGENT_DESCRIPTION": "<YOUR_AGENT_DESCRIPTION>",
        "AGENT_SYSTEM_PROMPT": "<YOUR_AGENT_SYSTEM_PROMPT>",
        "ANALYTICSTOOL": "True",
        "DEFAULT_AGENT_NAME": "<YOUR_DEFAULT_AGENT_NAME>",
        "INTEGRATIONSTOOL": "True",
        "NOTIFICATIONSTOOL": "True",
        "POSTIZ_AGENT_VERIFY": "<YOUR_POSTIZ_AGENT_VERIFY>",
        "POSTIZ_TOKEN": "<YOUR_POSTIZ_TOKEN>",
        "POSTIZ_URL": "<YOUR_POSTIZ_URL>",
        "POSTSTOOL": "True",
        "UPLOADSTOOL": "True",
        "VIDEOTOOL": "True"
      }
    }
  }
}

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

postiz_agent-0.9.0.tar.gz (15.4 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

postiz_agent-0.9.0-py3-none-any.whl (17.5 kB view details)

Uploaded Python 3

File details

Details for the file postiz_agent-0.9.0.tar.gz.

File metadata

  • Download URL: postiz_agent-0.9.0.tar.gz
  • Upload date:
  • Size: 15.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for postiz_agent-0.9.0.tar.gz
Algorithm Hash digest
SHA256 edf40057079da64981fa42a5ba833a173318be2e37aa7d8c00657dd2abd3add1
MD5 d29744543a2997487c07420a38888249
BLAKE2b-256 2edaf0b4fccb92a903d57db5c62bc32a3a081cfeacd33abb4b70435f8b1f410a

See more details on using hashes here.

File details

Details for the file postiz_agent-0.9.0-py3-none-any.whl.

File metadata

  • Download URL: postiz_agent-0.9.0-py3-none-any.whl
  • Upload date:
  • Size: 17.5 kB
  • Tags: Python 3
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.12.3

File hashes

Hashes for postiz_agent-0.9.0-py3-none-any.whl
Algorithm Hash digest
SHA256 6bbd57b2ab47860f261e5734a38e17047c4468a920b0862e976023cc706b26a3
MD5 c2024ec6b93e87164008016f8702dd96
BLAKE2b-256 8bd9e6c01b6e62b402350d6f8ae6ab08c381eac419419a0fb7eadab1c9db0aa0

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page